Multi-modal object re-identification (ReID) aims to retrieve specific targets by leveraging complementary cues from different sensing modalities. Despite recent progress, two key challenges remain: (1) the limited ability to jointly address both modality and viewpoint discrepancies, and (2) the difficulty of effectively leveraging reliable target-domain data to improve generalization. To address these challenges, we propose Proxy-driven Test-Time Training (ProxyTTT), a unified framework that enhances both multi-modal identity representation learning and model generalization. During training, we propose a Multi-Proxy Learning (MPL) mechanism to address the representation bias across different views and modalities. MPL disentangles fine-grained modality-specific and modality-common identity proxies as semantic anchors to align identity features across diverse perspectives and sensing modalities. This alignment strategy enables the model to learn robust and discriminative global identity representations under heterogeneous modality conditions. At test time, to reliably exploit target domain data, we propose Proxy-guided Entropy-based Selective Adaptation (PESA) for test-time training. Specifically, PESA leverages the semantic structure encoded by identity proxies to estimate prediction uncertainty via entropy, and selectively adapts the model using only high-confidence samples. This selective adaptation effectively mitigates the domain shift between training and deployment environments, improving the model’s generalization in real-world scenarios. Extensive experiments on four public multi-modal ReID benchmarks (RGBNT201, RGBNT100, MSVR310, and WMVeID863) demonstrate the effectiveness of ProxyTTT.

3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations for fully supervised learning, a process that is both time-consuming and costly. Semi-supervised learning (SSL) can address this by using a small amount of labeled data and a large amount of unlabeled data, improving performance while reducing the annotation costs. SSL adopts a teacher-student learning paradigm, where the teacher produces pseudo-labels to guide the student, often using high-confidence threshold filtering to improve pseudo-label quality. However, in the context of 3D-RES, where each label corresponds to a single mask and labeled data is scarce, existing SSL methods treat high-quality pseudo-labels merely as auxiliary supervision, which hinders their ability to fully boost the model's learning potential. The reliance on high-confidence thresholds for filtering often results in potentially valuable pseudo-labels being discarded, restricting the model's ability to leverage the abundant unlabeled data. Therefore, we identify two critical challenges in semi-supervised 3D-RES, namely, inefficient utilization of highquality pseudo-labels and wastage of useful information from lowquality pseudo-labels. In this paper, we introduce the first semisupervised learning framework for 3D-RES, presenting a robust baseline method named 3DResT. To address these challenges, we propose two novel designs called Teacher-Student Consistency- Based Sampling (TSCS) and Quality-Driven Dynamic Weighting (QDW). TSCS aids in the selection of high-quality pseudo-labels, integrating them into the labeled dataset to strengthen the labeled supervision signals. QDW preserves low-quality pseudo-labels by dynamically assigning them lower weights, allowing for the effective extraction of useful information rather than discarding them. Extensive experiments conducted on the widely used benchmark demonstrate the effectiveness of our method. Notably, with only 1 points compared to the fully supervised method. Code will be available at:https://github.com/Wind010321/3DResT

Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient updates. However, conventional mechanisms such as Gaussian and Laplacian noise are parameterized only by variance or scale. This single degree of freedom ties the magnitude of noise directly to both privacy loss and utility degradation, preventing independent control of these two factors. The problem becomes more pronounced when the number of composition rounds T and batch size B vary across tasks, as these variations induce task-dependent shifts in the privacy–utility trade-off, where small changes in noise parameters can disproportionately affect model accuracy. To address this limitation, we introduce PLRV-O, a framework that defines a broad search space of parameterized DP-SGD noise distributions, where privacy loss moments are tightly characterized yet can be optimized more independently with respect to utility loss. This formulation enables systematic adaptation of noise to task-specific requirements, including (i) model size, (ii) training duration, (iii) batch sampling strategies, and (iv) clipping thresholds under both training and fine-tuning settings. Empirical results demonstrate that PLRV-O substantially improves utility under strict privacy constraints. On CIFAR-10, a fine-tuned ViT achieves 94.03% accuracy at ∈ ≈ 0.5, compared to 83.93% with Gaussian noise. On SST-2, RoBERTa-large reaches 92.20% accuracy at ∈ ≈ 0.2, versus 50.25% with Gaussian. Source code is available at https://github.com/datasec-lab/plrvo.

Conditional diffusion models have gained increasing attention since their impressive results for cross-modal synthesis, where the strong alignment between conditioning input and generated output can be achieved by training a time-conditioned U-Net augmented with cross-attention mechanism. In this paper, we focus on the problem of generating music synchronized with rhythmic visual cues of the given dance video. Considering that bi-directional guidance is more beneficial for training a diffusion model, we propose to enhance the quality of generated music and its synchronization with dance videos by adopting both positive rhythmic information and negative ones (PN-Diffusion) as conditions, where a dual diffusion and reverse processes is devised. Specifically, to train a sequential multi-modal U-Net structure, PN-Diffusion consists of a noise prediction objective for positive conditioning and an additional noise prediction objective for negative conditioning. To accurately define and select both positive and negative conditioning, we ingeniously utilize temporal correlations in dance videos, capturing positive and negative rhythmic cues by playing them forward and backward, respectively. Through subjective and objective evaluations of input-output correspondence in terms of dance-music beat alignment and the quality of generated music, experimental results on the AIST++ and TikTok dance video datasets demonstrate that our model outperforms SOTA dance-to-music generation models.

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during training. However, mainstream DMs now consume increasingly large amounts of data. For example, training a Stable Diffusion model requires billions of image-text pairs. This enormous data requirement poses significant challenges for training large DMs due to high data acquisition costs and storage expenses. To alleviate this data burden, we propose a novel scenario: using existing DMs as data sources to train new DMs with any architecture. We refer to this scenario as Data-Free Knowledge Distillation for Diffusion Models (DKDM), where the generative ability of DMs is transferred to new ones in a data-free manner. To tackle this challenge, we make two main contributions. First, we introduce a DKDM objective that enables the training of new DMs via distillation, without requiring access to the data. Second, we develop a dynamic iterative distillation method that efficiently extracts time-domain knowledge from existing DMs, enabling direct retrieval of training data without the need for a prolonged generative process. To the best of our knowledge, we are the first to explore this scenario. Experimental results demonstrate that our data-free approach not only achieves competitive generative performance but also, in some instances, outperforms models trained with the entire dataset.

Dataset distillation aims to synthesize a small, information-rich dataset from a large one for efficient model training. However, existing dataset distillation methods struggle with long-tailed datasets, which are prevalent in real-world scenarios. By investigating the reasons behind this unexpected result, we identified two main causes: 1) The distillation process on imbalanced datasets develops biased gradients, leading to the synthesis of similarly imbalanced distilled datasets. 2) The experts trained on such datasets perform suboptimally on tail classes, resulting in misguided distillation supervision and poor-quality soft-label initialization. To address these issues, we first propose Distribution-agnostic Matching to avoid directly matching the biased expert trajectories. It reduces the distance between the student and the biased expert trajectories and prevents the tail class bias from being distilled to the synthetic dataset. Moreover, we improve the distillation guidance with Expert Decoupling, which jointly matches the decoupled backbone and classifier to improve the tail class performance and initialize reliable soft labels. This work pioneers the field of long-tailed dataset distillation, marking the first effective effort to distill long-tailed datasets. Our code will be made public at https://github.com/ichbill/LTDD.

Recent advancements in 3D Large Language Models (3DLLMs) have highlighted their potential in building general-purpose agents in the 3D real world, yet challenges remain due to the lack of high-quality robust instruction-following data, leading to limited discriminative power and generalization of 3DLLMs. In this paper, we introduce Robin3D, a powerful 3DLLM trained on large-scale instruction-following data generated by our novel data engine, Robust Instruction Generation (RIG) engine. RIG generates two key instruction data: 1) the Adversarial Instruction-following data, which features mixed negative and positive samples to enhance the model's discriminative understanding. 2) the Diverse Instruction-following data, which contains various instruction styles to enhance model's generalization. As a result, we construct 1 million instruction-following data, consisting of 344K Adversarial samples, 508K Diverse samples, and 165K benchmark training set samples. To better handle these complex instructions, Robin3D first incorporates Relation-Augmented Projector to enhance spatial understanding, and then strengthens the object referring and grounding ability through ID-Feature Bonding. Robin3D consistently outperforms previous methods across five widely-used 3D multimodal learning benchmarks, without the need for task-specific fine-tuning. Notably, we achieve a 7.8\% improvement in the grounding task (Multi3DRefer) and a 6.9\% improvement in the captioning task (Scan2Cap).

Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer features in the CLIP visual encoder, as the prefix content. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which further increases the number of visual tokens significantly. However, due to the inherent design of the Transformer architecture, the computational costs of these models tend to increase quadratically with the number of input tokens. To tackle this problem, we explore a token reduction mechanism that identifies significant spatial redundancy among visual tokens. In response, we propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs. Specifically, to metric the importance of each token, we exploit the sparsity observed in the visual encoder, characterized by the sparse distribution of attention scores between the class token and visual tokens. This sparsity enables us to dynamically select the most crucial visual tokens to retain. Subsequently, we cluster the selected (unpruned) tokens based on their key similarity and merge them with the unpruned tokens, effectively supplementing and enhancing their informational content. Empirically, when applied to LLaVA-1.5, our approach can compress the visual tokens by 14 times on average, and achieve comparable performance across diverse visual question-answering and reasoning tasks. Code and checkpoints are at https://llava-prumerge.github.io/.

The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on this approach, we further distinguish two critical types of quantized layers: those responsible for retaining essential temporal information and those particularly sensitive to bit-width reduction. By selectively finetuning these layers under both local and global supervision, we mitigate performance degradation while enhancing quantization efficiency. Our method demonstrates its efficacy across three high-resolution image generation tasks, obtaining state-of-the-art performance across multiple bit-width settings.

In real-life scenarios, humans seek out objects in the 3D world to fulfill their daily needs or intentions. This inspires us to introduce 3D intention grounding, a new task in 3D object detection employing RGB-D, based on human intention, such as "I want something to support my back." Closely related, 3D visual grounding focuses on understanding human reference. To achieve detection based on human intention, it relies on humans to observe the scene, reason out the target that aligns with their intention ("pillow" in this case), and finally provide a reference to the AI system, such as "A pillow on the couch". Instead, 3D intention grounding challenges AI agents to automatically observe, reason and detect the desired target solely based on human intention. To tackle this challenge, we introduce the new Intent3D dataset, consisting of 44,990 intention texts associated with 209 fine-grained classes from 1,042 scenes of the ScanNet dataset. We also establish several baselines based on different language-based 3D object detection models on our benchmark. Finally, we propose IntentNet, our unique approach, designed to tackle this intention-based detection problem. It focuses on three key aspects: intention understanding, reasoning to identify object candidates, and cascaded adaptive learning that leverages the intrinsic priority logic of different losses for multiple objective optimization.

The combination of computer vision and artificial intelligence is fundamentally transforming a broad spectrum of industries by enabling machines to interpret and act upon visual data with high levels of accuracy. As the biggest and by far the most popular open-source computer vision library, OpenCV library provides an extensive suite of programming functions supporting real-time computer vision. Bugs in the OpenCV library can affect the downstream computer vision applications, and it is critical to ensure the reliability of the OpenCV library. This paper introduces VistaFuzz, a novel technique for harnessing large language models (LLMs) for document-guided fuzzing of the OpenCV library. Vistafuzz utilizes LLMs to parse API documentation and obtain standardized API information. Based on this standardized information, Vista Fuzz extracts constraints on individual input parameters and dependencies between these. Using these constraints and dependencies, VistaFuzz then generates new input values to systematically test each target API. We evaluate the effectiveness of Vistafuzz in testing 330 APIs in the OpenCV library, and the results show that Vistafuzz detected 17 new bugs, where 10 bugs have been confirmed, and 5 of these have been fixed.

X-ray imaging is indispensable in medical diagnostics, yet its use is tightly regulated due to radiation exposure. Recent research borrows representations from the 3D reconstruction area to complete two tasks with reduced radiation dose: X-ray Novel View Synthesis (NVS) and Computed Tomography (CT) reconstruction. However, these representations fail to fully capture the penetration and attenuation properties of X-ray imaging as they originate from visible light imaging. In this paper, we introduce X-Field, a 3D representation informed in the physics of X-ray imaging. First, we employ homogeneous 3D ellipsoids with distinct attenuation coefficients to accurately model diverse materials within internal structures. Second, we introduce an efficient path-partitioning algorithm that resolves the intricate intersection of ellipsoids to compute cumulative attenuation along an X-ray path. We further propose a hybrid progressive initialization to refine the geometric accuracy of X-Field and incorporate material-based optimization to enhance model fitting along material boundaries. Experiments show that X-Field achieves superior visual fidelity on both real-world human organ and synthetic object datasets, outperforming state-of-the-art methods in X-ray NVS and CT Reconstruction. Our code is available on the project page: https://github.com/Brack-Wang/X-Field.

We present Orientation-anchored Gaussian Splatting (OriGS), a novel framework for high-quality 4D reconstruction from casually captured monocular videos. While recent advances extend 3D Gaussian Splatting to dynamic scenes via various motion anchors, such as graph nodes or spline control points, they often rely on low-rank assumptions and fall short in modeling complex, region-specific deformations inherent to unconstrained dynamics. OriGS addresses this by introducing a hyperdimensional representation grounded in scene orientation. We first estimate a Global Orientation Field that propagates principal forward directions across space and time, serving as stable structural guidance for dynamic modeling. Built upon this, we propose Orientation-aware Hyper-Gaussian, a unified formulation that embeds time, space, geometry, and orientation into a coherent probabilistic state. This enables inferring region-specific deformation through principled conditioned slicing, adaptively capturing diverse local dynamics in alignment with global motion intent. Experiments demonstrate the superior reconstruction fidelity of OriGS over mainstream methods in challenging real-world dynamic scenes.

Dataset distillation aims to synthesize a small dataset from a large dataset, enabling the model trained on it to perform well on the original dataset. With the blooming of large language models and multimodal large language models, the importance of multimodal datasets, particularly image-text datasets, has grown significantly. However, existing multimodal dataset distillation methods are constrained by the Matching Training Trajectories algorithm, which significantly increases the computing resource requirement, and takes days to process the distillation. In this work, we introduce EDGE, a generative distillation method for efficient multimodal dataset distillation. Specifically, we identify two key challenges of distilling multimodal datasets with generative models: 1) The lack of correlation between generated images and captions. 2) The lack of diversity among generated samples. To address the aforementioned issues, we propose a novel generative model training workflow with a bi-directional contrastive loss and a diversity loss. Furthermore, we propose a caption synthesis strategy to further improve text-to-image retrieval performance by introducing more text information. Our method is evaluated on Flickr30K, COCO, and CC3M datasets, demonstrating superior performance and efficiency compared to existing approaches. Notably, our method achieves results 18$\times$ faster than the state-of-the-art method. Our code will be made public at https://github.com/ichbill/EDGE.

Video inpainting aims to fill in the missing regions of the video frames with plausible content. Benefiting from the outstanding long-range modeling capacity, the transformer-based models have achieved unprecedented performance regarding inpainting quality. Essentially, coherent contents from all the frames along both spatial and temporal dimensions are concerned by a patch-wise attention module, and then the missing contents are generated based on the attention-weighted summation. In this way, attention retrieval accuracy has become the main bottleneck to improve the video inpainting performance, where the factors affecting attention calculation should be explored to maximize the advantages of transformer. Towards this end, in this paper, we theoretically certificate that noise is the culprit that entangles the process of attention calculation. Meanwhile, we propose a novel wavelet transformer network with noise robustness for video inpainting, named WaveFormer. Unlike existing transformer-based methods that utilize the whole embeddings to calculate the attention, our WaveFormer first separates the noise existing in the embedding into high-frequency components by introducing the Discrete Wavelet Transform (DWT), and then adopts clean low-frequency components to calculate the attention. In this way, the impact of noise on attention computation can be greatly mitigated and the missing content regarding different frequencies can be generated by sharing the calculated attention. Extensive experiments validate the superior performance of our method over state-of-the-art baselines both qualitatively and quantitatively.

Multi-task learning for dense prediction has emerged as a pivotal area in computer vision, enabling simultaneous processing of diverse yet interrelated pixel-wise prediction tasks. However, the substantial computational demands of state-of-the-art (SoTA) models often limit their widespread deployment. This paper addresses this challenge by introducing network binarization to compress resource-intensive multi-task dense predictors. Specifically, our goal is to significantly accelerate multi-task dense prediction models via Binary Neural Networks (BNNs) while maintaining and even improving model performance at the same time. To reach this goal, we propose a Binary Multi-task Dense Predictor, Bi -MTPD, and several variants of Bi -MTPD, in which a multi-task dense predictor is constructed via specified binarized modules. Our systematical analysis of this predictor reveals that performance drop from binarization is primarily caused by severe information degradation. To address this issue, we introduce a deep information bottleneck layer that enforces representations for downstream tasks satisfying Gaussian distribution in forward propagation. Moreover, we introduce a knowledge distillation mechanism to correct the direction of information flow in backward propagation. Intriguingly, one variant of Bi -MTPD outperforms full-precision (FP) multi-task dense prediction SoTAs, ARTC [2] (CNN-based) and InvPT [50] (ViT-Based). This result indicates that Bi -MTPD is not merely a naive trade-off between performance and efficiency, but is rather a benefit of the redundant information flow thanks to the multi-task architecture. Code is available at BiMTDP.

Post-training quantization (PTQ) converts a pre-trained full-precision (FP) model into a quantized model in a training-free manner. Determining suitable quantization parameters, such as scaling factors and zero points, is the primary strategy for mitigating the impact of quantization noise (calibration) and restoring the performance of the quantized models. However, the existing activation calibration methods have never considered information degradation between pre- (FP) and post-quantized activations. In this study, we introduce a well-defined distributional metric from information theory, mutual information, into PTQ calibration. We aim to calibrate the quantized activations by maximizing the mutual information between the pre- and post-quantized activations. To realize this goal, we establish a contrastive learning (CL) framework for the calibration, where the quantization parameters are optimized through a self-supervised proxy task. Specifically, by leveraging CL during the PTQ calibration, we can benefit from pulling the positive pairs of quantized and FP activations collected from the same input samples, while pushing negative pairs from different samples. Thanks to the ingeniously designed critic function, we avoid the unwanted but of tenencountered collision solution in CL, especially in calibration scenarios where the amount of calibration data is limited. Additionally, we provide a theoretical guarantee that minimizing our designed loss is equivalent to maximizing the desired mutual information. Consequently, the quantized activations retain more information, which ultimately enhances the performance of the quantized network. Experimental results show that our method can effectively serve as an add-on module to existing SoTA PTQ methods.

While Transformers have rapidly gained popularity in various computer vision applications, post-hoc explanations of their internal mechanisms remain largely unexplored. Vision Transformers extract visual information by representing image regions as transformed tokens and integrating them via attention weights. However, existing post-hoc explanation methods merely consider these attention weights, neglecting crucial information from the transformed tokens, which fails to accurately illustrate the rationales behind the models' predictions. To incorporate the influence of token transformation into interpretation, we propose TokenTM, a novel post-hoc explanation method that utilizes our introduced measurement of token transformation effects. Specifically, we quantify token transformation effects by measuring changes in token lengths and correlations in their directions pre- and post-transformation. Moreover, we develop initialization and aggregation rules to integrate both attention weights and token transformation effects across all layers, capturing holistic token contributions throughout the model. Experimental results on segmentation and perturbation tests demonstrate the superiority of our proposed TokenTM compared to state-of-the-art Vision Transformer explanation methods.

To interpret Vision Transformers, post-hoc explanations assign salience scores to input pixels, providing human-understandable heatmaps. However, whether these inter-pretations reflect true rationales behind the model's output is still underexplored. To address this gap, we study the faithfulness criterion of explanations: the assigned salience scores should represent the influence of the corresponding input pixels on the model's predictions. To evaluate faithful-ness, we introduce Salience-guided Faithfulness Coefficient (SaCo), a novel evaluation metric leveraging essential in-formation of salience distribution. Specifically, we con-duct pair-wise comparisons among distinct pixel groups and then aggregate the differences in their salience scores, resulting in a coefficient that indicates the explanation's degree of faithfulness. Our explorations reveal that cur-rent metrics struggle to differentiate between advanced ex-planation methods and Random Attribution, thereby failing to capture the faithfulness property. In contrast, our pro-posed SaCo offers a reliable faithfulness measurement, es-tablishing a robust metric for interpretations. Furthermore, our SaCo demonstrates that the use of gradient and multi-layer aggregation can markedly enhance the faithfulness of attention-based explanation, shedding light on potential paths for advancing Vision Transformer explainability.

Route planning for navigation under partial observability plays a crucial role in modern robotics and autonomous driving. Existing route planning approaches can be categorized into two main classes: traditional autoregressive and diffusion-based methods. The former often fails due to its myopic nature, while the latter either assumes full observability or struggles to adapt to unfamiliar scenarios, due to strong couplings with behavior cloning from experts. To address these deficiencies, we propose a versatile diffusion-based approach for both 2D and 3D route planning under partial observability. Specifically, our value-guided diffusion policy first generates plans to predict actions across various timesteps, providing ample foresight to the planning. It then employs a differentiable planner with state estimations to derive a value function, directing the agent's exploration and goal-seeking behaviors without seeking experts while explicitly addressing partial observability. During inference, our policy is further enhanced by a best-plan-selection strategy, substantially boosting the planning success rate. Moreover, we propose projecting point clouds, derived from RGB-D inputs, onto 2D grid-based bird-eye- view maps via semantic segmentation, generalizing to 3D environments. This simple yet effective adaption enables zero-shot transfer from 2D-trained policy to 3D, cutting across the laborious training for 3D policy, and thus certifying our versatility. Experimental results demonstrate our superior performance, particularly in navigating situations beyond expert demonstrations, surpassing state-of-the-art autoregressive and diffusion-based baselines for both 2D and 3D scenarios.

Knowledge distillation (KD), which distills knowledge from complex networks (teacher) to lightweight (student) networks, has been actively studied recently. Despite previous studies have proposed several advanced KD losses or intricate training strategies, the core concept of KD proves ineffective if the student model is too weak to mimic the teacher's performance. In this study, we aim to narrow the performance discrepancy between Transformer-based teacher and student models by incorporating the inductive biases of several heterogeneous student models. To this end, we put forward a novel cross-architecture knowledge distillation approach called Adaptive Cross-architecture Mutual Knowledge Distillation (ACMKD), which tries to mitigate the performance gap issue using a multi-students mutual learning strategy. Specifically, we utilize three mainstream models associated with various inductive biases (CNN, INN, and Transformer) as the student models. In addition, we propose an effective attention similarity mechanism to facilitate the student models in mimicking specific portions of the teacher model. Drawing inspiration from the Cannikin Law, we devise a unique second-stage KD process that dynamically enables the weakest student model to learn from other stronger student models again. We validate our proposed methods on ImageNet and CIFAR100 datasets, and the results confirm that our ACMKD method significantly narrows the performance gap compared to other KD methods.

The purpose of video inpainting is to fill a specified area with reasonable content. However, in the case of multiple targets and complex textures, current methods struggle to distinguish between feature information of the targets, leading to confusing or fuzzy inpainting results. In this paper, we design a new text-video completion network based on a motion compensation and temporal attention feature aggregation. Our network utilizes information from reference frames and target frames to complete the damaged region of the target frame. We first employ motion compensation to align the features of reference frames, and then use the temporal attention module to aggregate these features, resulting in accurate and reasonable content. To evaluate the effectiveness of our method, we introduce a new text video dataset with multiple text objects and complex textures, presenting a novel and challenging task for inpainting research. Through quantitative and qualitative comparison experiments, we demonstrate that our model outperforms existing baseline models in scenarios with multiple objects and complex textures.

Most AI systems rely on the premise that the input visual data are sufficient to achieve competitive performance in various tasks. However, the classic task setup rarely considers the challenging, yet common practical situations where the complete visual data may be inaccessible due to various reasons (e.g., restricted view range and occlusions). To this end, we investigate a task setting with incomplete visual input data. Specifically, we exploit the Scene Graph Generation (SGG) task with various levels of visual data missingness as input. While insufficient visual input naturally leads to performance drop, we propose to supplement the missing visions via natural language dialog interactions to better accomplish the task objective. We design a model-agnostic Supplementary Interactive Dialog (SI-Dial) framework that can be jointly learned with most existing models, endowing the current AI systems with the ability of question-answer interactions in natural language. We demonstrate the feasibility of such task setting with missing visual input and the effectiveness of our proposed dialog module as the supplementary information source through extensive experiments, by achieving promising performance improvement over multiple baselines.

This paper presents a novel Fully Binary Point Cloud Transformer (FBPT) model which has the potential to be widely applied and expanded in the fields of robotics and mobile devices. By compressing the weights and activations of a 32-bit full-precision network to 1-bit binary values, the proposed binary point cloud Transformer network significantly reduces the storage footprint and computational resource requirements of neural network models for point cloud processing tasks, compared to full-precision point cloud networks. However, achieving a fully binary point cloud Transformer network, where all parts except the modules specific to the task are binary, poses challenges and bottlenecks in quantizing the activations of Q, K, V and self-attention in the attention module, as they do not adhere to simple probability distributions and can vary with input data. Furthermore, in our network, the binary attention module undergoes a degradation of the self-attention module due to the uniform distribution that occurs after the softmax operation. The primary focus of this paper is on addressing the performance degradation issue caused by the use of binary point cloud Transformer modules. We propose a novel binarization mechanism called dynamic-static hybridization. Specifically, our approach combines static binarization of the overall network model with fine granularity dynamic binarization of data-sensitive components. Furthermore, we make use of a novel hierarchical training scheme to obtain the optimal model and binarization parameters. These above improvements allow the proposed binarization method to outperform binarization methods applied to convolution neural networks when used in point cloud Transformer structures. To demonstrate the superiority of our algorithm, we conducted experiments on two different tasks: point cloud classification and place recognition. In point cloud classification, our model achieved an accuracy of 90.9%, which is only a 2.3% decrease compared to the full precision network. For the place recognition task, we achieved 91.02% in the top @1% metric and 82.87% in the top @1% metric on the Oxford RobotCar dataset in terms of the average recall rate. Moreover, our model exhibits a significant reduction of over 80% in terms of model size and FLOPs (floating-point operations) compared to the baseline.

This paper enhances model-based offline inverse reinforcement learning (IRL) by refining conservative Markov decision process (MDP) frameworks, traditionally employing uncertainty penalties to deter exploitation in uncertain areas. Existing methods, dependent on neural network ensembles to model MDP dynamics and quantify uncertainty through ensemble prediction heuristics, face limitations: they presume Gaussian-distributed state transitions, leading to simplified environmental representations. Additionally, ensemble modeling often results in high variance, indicating potential overfitting and a lack of generalizability. Moreover, the heuristic reliance for uncertainty quantification struggles to fully grasp environmental complexities, offering an incomplete foundation for informed decisions. Maintaining multiple models also demands substantial computational resources. Addressing these shortcomings, we propose leveraging score-based diffusion generative models for dynamic modeling. This method significantly broadens the scope of representable target distributions, surpassing Gaussian constraints. It not only improves the accuracy of transition modeling but also roots uncertainty quantification in diffusion models’ theoretical underpinnings, enabling more precise and dependable reward regularization. We further innovate by incorporating a transition stability regularizer (TSR) into the reward estimation. This novel element embeds stability into the reward learning process, diminishing the influence of transition variability and promoting more consistent policy optimization. Our empirical studies on diverse Mujoco robotic control tasks demonstrate that our diffusion-based methodology not only furnishes more accurate transition estimations but also surpasses conventional ensemble approaches in policy effectiveness. The addition of the TSR marks a distinctive advancement in offline IRL by enhancing the reward and policy learning efficacy. Code: https://github.com/GabrielZH/doc-irl.

Whole-body pose estimation aims to regress human pose models that include the body, hand, and facial details from RGB images. While the task of whole-body mesh recovery has been extensively studied in recent literature, the focus has predominantly been on human mesh recovery for a single person, despite the frequent occurrence of multiple people in practical scenarios. Similar to body-only cases, such single-person whole-body pose estimation methods often fail in the multiple-people problem for two reasons: (i) Given the ambiguous bounding box, which could contain more than one instance, it is difficult for single-person-oriented methods to regress the body mesh model of the target person. (ii) Single-person pose estimation approaches neglect the person-person occlusions and the depth order among instances, thus generating interpenetrated models. In this paper, we propose the Multi-person Expressive POse (MEPO) model, which exploits expressive 3D human model reconstruction for multiple people. To our best knowledge, our model is the first multi-person whole-body mesh reconstruction model, which is intensified by heatmap, depthmap, and depth order loss. We propose the Heatmap Enhancement Net (HENet) to leverage the heatmap information to assist the model in concentrating on the target person in crowded multi-person cases, while the depthmap delivers depth information of the image. Furthermore, we impose a depth order loss to recover human mesh precisely for overlapped people. In our experiments, we evaluate our model on multiple challenging datasets, including AGORA, which consists of complex occlusions similar to real-world scenarios. Our method has a significant performance improvement compared with the state-of-the-art pose estimation methods.

Supervised cross-modal retrieval (CMR) achieves excellent performance thanks to the semantic information provided by its labels, which helps to establish semantic correlations between samples from different modalities. However, in real-world scenarios, there often exists a large amount of unlabeled and unpaired multimodal training data, rendering existing methods unfeasible. To address this issue, we propose a novel partially aligned cross-modal retrieval method called Optimal Transport-based Prototype Alignment Learning (OTPAL). Due to the high computational complexity involved in directly establishing matching correlations between unannotated unaligned cross-modal samples, instead, we establish matching correlations between shared prototypes and samples. To be specific, we employ the optimal transport algorithm to establish cross-modal alignment information between samples and prototypes, and then minimize the distance between samples and their corresponding prototypes through a specially designed prototype alignment loss. As an extension of this paper, we also extensively investigate the influence of incomplete multimodal data on cross-modal retrieval performance under the partially aligned setting proposed above. To further address the above more challenging scenario, we raise a scalable prototype-based neighbor feature completion method, which better captures the correlations between incomplete samples and neighbor samples through a cross-modal self-attention mechanism. Experimental results on four benchmark datasets show that our method can obtain satisfactory accuracy and scalability in various real-world scenarios.

The recent introduction of Diffusion Transformers (DiTs) has demonstrated exceptional capabilities in image generation by using a different backbone architecture, departing from traditional U-Nets and embracing the scalable nature of transformers. Despite their advanced capabilities, the wide deployment of DiTs, particularly for real-time applications, is currently hampered by considerable computational demands at the inference stage. Post-training Quantization (PTQ) has emerged as a fast and data-efficient solution that can significantly reduce computation and memory footprint by using low-bit weights and activations. However, its applicability to DiTs has not yet been explored and faces non-trivial difficulties due to the unique design of DiTs. In this paper, we propose PTQ4DiT, a specifically designed PTQ method for DiTs. We discover two primary quantization challenges inherent in DiTs, notably the presence of salient channels with extreme magnitudes and the temporal variability in distributions of salient activation over multiple timesteps. To tackle these challenges, we propose Channel-wise Salience Balancing (CSB) and Spearmen's $\rho$-guided Salience Calibration (SSC). CSB leverages the complementarity property of channel magnitudes to redistribute the extremes, alleviating quantization errors for both activations and weights. SSC extends this approach by dynamically adjusting the balanced salience to capture the temporal variations in activation. Additionally, to eliminate extra computational costs caused by PTQ4DiT during inference, we design an offline re-parameterization strategy for DiTs. Experiments demonstrate that our PTQ4DiT successfully quantizes DiTs to 8-bit precision (W8A8) while preserving comparable generation ability and further enables effective quantization to 4-bit weight precision (W4A8) for the first time.

Semi-supervised cross-modal retrieval (SS-CMR) aims at learning modality invariance and semantic discrimination from labeled data and unlabeled data, which is crucial for practical applications in the real-world. The key to essentially addressing the SS-CMR task is to solve the semantic association and modality heterogeneity problems. To address these issues, in this paper, we propose a novel semi-supervised cross-modal retrieval method, namely Semi-supervised Prototype Semantic Association Learning (SPAL) for robust cross-modal retrieval. To be specific, we employ shared semantic prototypes to associate labeled and unlabeled data over both modalities to minimize intra-class and maximize inter-class variations, thereby improving discriminative representations on unlabeled data. What is more important is that we propose a novel pseudo-label guided contrastive learning to refine cross-modal representation consistency in the common space, which leverages pseudo-label semantic graph information to constrain cross-modal consistent representations. Meanwhile, multi-modal data inevitably suffers from the cost and difficulty of data collection, resulting in the incomplete multimodal data problem. Thus, to strengthen the robustness of the SS-CMR, we propose a novel prototype propagation method for incomplete data to reconstruct completion representations which preserves the semantic consistency. Extensive evaluations using several baseline methods across four benchmark datasets demonstrate the effectiveness of our method.

We introduce a novel weakly-supervised video actor-action segmentation (VAAS) framework, where only video-level tags are available. Previous VAAS methods follow a synthesize-and-refine scheme, i.e., they first synthesize the pseudo-segmentation and recursively refine the segmentation. However, this process requires significant time costs and heavily relies on the quality of the initial segmentation. Unlike existing works, our method hierarchically mines contrastive relations to supplement each other for learning a visually-plausible segmentation model. Specifically, three contrastive relations are abstracted from the pixel-level and frame-level, i.e., low-level edge-aware, class-activation map aware, and semantic tag-aware relations. Then, the discovered contrastive relations are unified into a universal objective for training the segmentation model, regardless of their heterogeneity. Moreover, we incorporate motion cues and unlabeled samples to increase the discriminative power and robustness of the segmentation model. Extensive experiments indicate that our proposed method produces reasonable segmentation.

By observing a scene and listening to corresponding audio cues, humans can easily recognize where the sound is. To achieve such cross-modal perception on machines, existing methods take advantage of the maps obtained by interpolation operations to localize the sound source. As semantic object-level localization is more attractive for prospective practical applications, we argue that these map-based methods only offer a coarse-grained and indirect description of the sound source. Additionally, these methods utilize a single audio-visual tuple at a time during self-supervised learning, causing the model to lose the crucial chance to reason about the data distribution of large-scale audio-visual samples. Although the introduction of Audio-Visual Contrastive Learning (AVCL) can effectively alleviate this issue, the contrastive set constructed by randomly sampling is based on the assumption that the audio and visual segments from all other videos are not semantically related. Since the resulting contrastive set contains a large number of faulty negatives, we believe that this assumption is rough. In this paper, we advocate a novel proposal-based solution that directly localizes the semantic object-level sound source, without any manual annotations. The Global Response Map (GRM) is incorporated as an unsupervised spatial constraint to filter those instances corresponding to a large number of sound-unrelated regions. As a result, our proposal-based Sound Source Localization (SSL) can be cast into a simpler Multiple Instance Learning (MIL) problem. To overcome the limitation of random sampling in AVCL, we propose a novel Active Contrastive Set Mining (ACSM) to mine the contrastive sets with informative and diverse negatives for robust AVCL. Our approaches achieve state-of-the-art (SOTA) performance when compared to several baselines on multiple SSL datasets with diverse scenarios.

We are perceiving and communicating with the world in a multisensory manner, where different information sources are sophisticatedly processed and interpreted by separate parts of the human brain to constitute a complex, yet harmonious and unified sensing system. To endow the machines with true intelligence, multimodal machine learning that incorporates data from various sources has become an increasingly popular research area with emerging technical advances in recent years. In this paper, we present a survey on multimodal machine learning from a novel perspective considering not only the purely technical aspects but also the intrinsic nature of different data modalities. We analyze the commonness and uniqueness of each data format mainly ranging from vision, audio, text, and motions, and then present the methodological advancements categorized by the combination of data modalities, such as Vision+Text, with slightly inclined emphasis on the visual data. We investigate the existing literature on multimodal learning from both the representation learning and downstream application levels, and provide an additional comparison in the light of their technical connections with the data nature, e.g., the semantic consistency between image objects and textual descriptions, and the rhythm correspondence between video dance moves and musical beats. We hope that the exploitation of the alignment as well as the existing gap between the intrinsic nature of data modality and the technical designs, will benefit future research studies to better address a specific challenge related to the concrete multimodal task, prompting a unified multimodal machine learning framework closer to a real human intelligence system.

Automatic tooth instance segmentation on 3D dental models is crucial for digitizing dental treatments and enabling computer-assisted treatment planning. However, It is challenging since the tight arrangement of dental structures and the consequential impact of dental ailments on their morphological characteristics. To address these challenges, we propose a novel method called THISNet. Unlike existing methods, THISNet focuses on highlighting tooth regions rather than relying on bounding box detection, leading to improved accuracy in tooth segmentation and labeling. By incorporating the highlighted tooth regions with a tooth object affinity module, our method effectively integrates global contextual information, considering the relationships between neighboring teeth and their surrounding structures. THISNet adopts an end-to-end learning approach, reducing complexity and enhancing segmentation efficiency compared to multi-stage training methods. Experimental results demonstrate the superiority of THISNet over existing approaches, highlighting its potential in various dental clinical applications.

Current talking face generation methods have achieved promising lip-synchronization results, while still struggling to generate talking face video that exhibits emotional expressions and head poses. Studies in psychology have demonstrated that people may manifest diverse facial animations that follow a time-varying distribution. This presents two stochastic challenges that make generating appropriate emotional expressions and head poses difficult: (1) modelling the time-varying distribution of facial deformations to synthesize the stochastic dynamics of emotional expressions and head poses, and (2) estimating the complex motion distribution with given audio features to capture ambiguous audio-related expressions and head poses. To address the above issues, we present a Stochastic Latent talkIng face Generation mOdel (SLIGO), which builds a deep state space model (SSM) for talking face generation. The SLIGO model captures diverse and stochastic facial dynamics via the latent motion distribution. Additionally, we devise a dynamic variational autoencoder (DVAE) method to optimize the deep SSM model. This method decomposes the Evidence Lower BOund (ELBO) of SSM into three components: a posterior for latent motion encoding, a prior for audio-driven motion prediction, and a likelihood for talking face decoding. Furthermore, we propose a novel mixer continuous normalizing flow (CNF) module to model the complex facial motion prior distribution. Experimental results demonstrate that SLIGO outperforms existing methods and achieves state-of-the-art performance.

Audio-visual matching is an essential task that measures the correlation between audio clips and visual images. However, current methods rely solely on the joint embedding of global features from audio clips and face image pairs to learn semantic correlations. This approach overlooks the importance of high-confidence correlations and discrepancies of local subtle features, which are crucial for cross-modal matching. To address this issue, we propose a novel Attribute-guided Cross-modal Interaction and Enhancement Network (ACIENet), which employs multiple attributes to explore the associations of different key local subtle features. The ACIENet contains two novel modules: the Attribute-guided Interaction (AGI) module and the Attribute-guided Enhancement (AGE) module. The AGI module employs global feature alignment similarity to guide cross-modal local feature interactions, which enhances cross-modal association features for the same identity and expands cross-modal distinctive features for different identities. Additionally, the interactive features and original features are fused to ensure intra-class discriminability and inter-class correspondence. The AGE module captures subtle attribute-related features by using an attribute-driven network, thereby enhancing discrimination at the attribute level. Specifically, it strengthens the combined attribute-related features of gender and nationality. To prevent interference between multiple attribute features, we design a multi-attribute learning network as a parallel framework. Experiments conducted on a public benchmark dataset demonstrate the efficacy of the ACIENet method in different scenarios. Code and models are available at https://github.com/w1018979952/ACIENet.

Denoising diffusion (score-based) generative models have recently achieved significant accomplishments in generating realistic and diverse data. Unfortunately, the generation process of current denoising diffusion models is notoriously slow due to the lengthy iterative noise estimations, which rely on cumbersome neural networks. It prevents the diffusion models from being widely deployed, especially on edge devices. Previous works accelerate the generation process of diffusion model (DM) via finding shorter yet effective sampling trajectories. However, they overlook the cost of noise estimation with a heavy network in every iteration. In this work, we accelerate generation from the perspective of compressing the noise estimation network. Due to the difficulty of retraining DMs, we exclude mainstream training-aware compression paradigms and introduce post-training quantization (PTQ) into DM acceleration. However, the output distributions of noise estimation networks change with time-step, making previous PTQ methods fail in DMs since they are designed for single-time step scenarios. To devise a DM-specific PTQ method, we explore PTQ on DM in three aspects: quantized operations, calibration dataset, and calibration metric. We summarize and use several observations derived from all-inclusive investigations to formulate our method, which especially targets the unique multi-time-step structure of DMs. Experimentally, our method can directly quantize full-precision DMs into 8-bit models while maintaining or even improving their performance in a training-free manner. Importantly, our method can serve as a plug-and-play module on other fast-sampling methods, e.g., DDIM [24]. The code is available at https://https://github.com/42Shawn/PTQ4DM.

Stereo video inpainting aims to fill the missing regions on the left and right views of the stereo video with plausible content simultaneously. Compared with the single video inpainting that has achieved promising results using deep convolutional neural networks, inpainting the missing regions of stereo video has not been thoroughly explored. In essence, apart from the spatial and temporal consistency that single video inpainting needs to achieve, another key challenge for stereo video inpainting is to maintain the stereo consistency between left and right views and hence alleviate the 3D fatigue for viewers. In this paper, we propose a novel deep stereo video inpainting network named SVINet, which is the first attempt for stereo video inpainting task utilizing deep convolutional neural networks. SVINet first utilizes a self-supervised flow-guided deformable temporal alignment module to align the features on the left and right view branches, respectively. Then, the aligned features are fed into a shared adaptive feature aggregation module to generate missing contents of their respective branches. Finally, the parallax attention module (PAM) that uses the cross-view information to consider the significant stereo correlation is introduced to fuse the completed features of left and right views. Furthermore, we develop a stereo consistency loss to regularize the trained parameters, so that our model is able to yield high-quality stereo video inpainting results with better stereo consistency. Experimental results demonstrate that our SVINet outperforms state-of-the-art single video inpainting models.

Deep learning-based video inpainting has yielded promising results and gained increasing attention from re-searchers. Generally, these methods assume that the cor-rupted region masks of each frame are known and easily ob-tained. However, the annotation of these masks are labor-intensive and expensive, which limits the practical application of current methods. Therefore, we expect to relax this assumption by defining a new semi-supervised inpainting setting, making the networks have the ability of completing the corrupted regions of the whole video using the anno-tated mask of only one frame. Specifically, in this work, we propose an end-to-end trainable framework consisting of completion network and mask prediction network, which are designed to generate corrupted contents of the current frame using the known mask and decide the regions to be filled of the next frame, respectively. Besides, we introduce a cycle consistency loss to regularize the training parameters of these two networks. In this way, the completion network and the mask prediction network can constrain each other, and hence the overall performance of the trained model can be maximized. Furthermore, due to the natural existence of prior knowledge (e.g., corrupted contents and clear bor-ders), current video inpainting datasets are not suitable in the context of semi-supervised video inpainting. Thus, we create a new dataset by simulating the corrupted video of real-world scenarios. Extensive experimental results are reported to demonstrate the superiority of our model in the video inpainting task. Remarkably, although our model is trained in a semi-supervised manner, it can achieve compa-rable performance as fully-supervised methods.

Video inpainting aims to utilize plausible contents to fill missing regions in the video. State-of-the-art video inpainting methods typically generate the missing contents of the target frame (current frame) by aggregating the temporal information of reference frames (neighboring frames) aligned using deformable convolution. However, these deformable convolution alignment networks often suffer from offset overflow during training, resulting in unsatisfactory alignment, thereby obtaining compromised inpainting performance. In this paper, we propose a self-supervised Flow-Guided Deformable Alignment (FGDA) network for aligning reference frames at the feature level. FGDA computes the residual of the optical flow as the offsets. This design can effectively reduce the burden of offsets learning, thereby avoiding offset overflow. Furthermore, a gradient-weighted reconstruction loss for supervised completed frame reconstruction is designed, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed texture regions, so that detail textures get more attention during training. Experiments show that FGDA-based video inpainting model trained with gradient-weighted reconstruction loss outperforms the state-of-the-art by a significant margin in terms of PSNR and SSIM with relative improvements of 6.2% and 2.1%, respectively.

Brain vessel image segmentation can be used as a promising biomarker for better prevention and treatment of different diseases. One successful approach is to consider the segmentation as an image-to-image translation task and perform a conditional Generative Adversarial Network (cGAN) to learn a transformation between two distributions. In this paper, we present a novel multi-view approach, MLP-GAN, which splits a 3D volumetric brain vessel image into three different dimensional 2D images (i.e., sagittal, coronal, axial) and then feed them into three different 2D cGANs. The proposed MLP-GAN not only alleviates the memory issue which exists in the original 3D neural networks but also retains 3D spatial information. Specifically, we utilize U-Net as the backbone for our generator and redesign the pattern of skip connection integrated with the MLP-Mixer [1] which has attracted lots of attention recently. Our model obtains the ability to capture cross-patch information to learn global information with the MLP-Mixer. Extensive experiments are performed on the public brain vessel dataset [2] that show our MLP-GAN outperforms other state-of-the-art methods.

With recent advances in computing hardware and surges of deep-learning architectures, learning-based deep image registration methods have surpassed their traditional counterparts, in terms of metric performance and inference time. However, these methods focus on improving performance measurements such as Dice, resulting in less attention given to model behaviors that are equally desirable for registrations, especially for medical imaging. This paper investigates these behaviors for popular learning-based deep registrations under a sanity-checking microscope. We find that most existing registrations suffer from low inverse consistency and nondiscrimination of identical pairs due to overly optimized image similarities. To rectify these behaviors, we propose a novel regularization-based sanity-enforcer method that imposes two sanity checks on the deep model to reduce its inverse consistency errors and increase its discriminative power simultaneously. Moreover, we derive a set of theoretical guarantees for our sanity-checked image registration method, with experimental results supporting our theoretical findings and their effectiveness in increasing the sanity of models without sacrificing any performance.

Model quantization, which aims to compress deep neural networks and accelerate inference speed, has greatly facilitated the development of cumbersome models on mobile and edge devices. There is a common assumption in quantization methods from prior works that training data is available. In practice, however, this assumption cannot always be fulfilled due to reasons of privacy and security, rendering these methods inapplicable in real-life situations. Thus, data-free network quantization has recently received significant attention in neural network compression. Causal reasoning provides an intuitive way to model causal relationships to eliminate data-driven correlations, making causality an essential component of analyzing data-free problems. However, causal formulations of data-free quantization are inadequate in the literature. To bridge this gap, we construct a causal graph to model the data generation and discrepancy reduction between the pre-trained and quantized models. Inspired by the causal understanding, we propose the Causality-guided Data-free Network Quantization method, Causal-DFQ, to eliminate the reliance on data via approaching an equilibrium of causality-driven intervened distributions. Specifically, we design a content-style-decoupled generator, synthesizing images conditioned on the relevant and irrelevant factors; then we propose a discrepancy reduction loss to align the intervened distributions of the pre-trained and quantized models. It is worth noting that our work is the first attempt towards introducing causality to data-free quantization problem. Extensive experiments demonstrate the efficacy of Causal-DFQ. The code is available at Causal-DFQ.

The goal of video inpainting is to fill in missing regions with reasonable and coherent content in a video sequence. Due to the motion of cameras and objects, the reference frame and the target frame are not aligned, and the useful information of the reference frame cannot be well utilized. Therefore, temporal alignment plays an important role in video inpainting. Some studies have attempted to divide the remote alignment into multiple sub-alignments and process them step by step, but error accumulation is inevitable. In this paper, we present a novel progressive feature alignment and temporal attention fusion network, namely PFTA-Net. Specifically, we design a progressive feature alignment module, which employs sub-alignments with a progressive refinement scheme, resulting in more accurate motion compensation. After alignment, we propose a temporal attention fusion module, which computes temporal attention weights for each aligned reference frame feature, resulting in modulated features for reconstructing the target frame. Our extensive evaluations, including both quantitative and qualitative assessments, demonstrate the better performance and efficacy of our video inpainting network.

Dataset distillation (DD) aims to synthesize a small dataset whose test performance is comparable to a full dataset using the same model. State-of-the-art (SoTA) methods optimize synthetic datasets primarily by matching heuristic indicators extracted from two networks: one from real data and one from synthetic data (see Fig.1, Left), such as gradients and training trajectories. DD is essentially a compression problem that emphasizes on maximizing the preservation of information contained in the data. We argue that well-defined metrics which measure the amount of shared information between variables in information theory are necessary for success measurement, but are never considered by previous works. Thus, we introduce mutual information (MI) as the metric to quantify the shared information between the synthetic and the real datasets, and devise MIM4DD numerically maximizing the MI via a newly designed optimizable objective within a contrastive learning framework to update the synthetic dataset. Specifically, we designate the samples in different datasets who share the same labels as positive pairs, and vice versa negative pairs. Then we respectively pull and push those samples in positive and negative pairs into contrastive space via minimizing NCE loss. As a result, the targeted MI can be transformed into a lower bound represented by feature maps of samples, which is numerically feasible. Experiment results show that MIM4DD can be implemented as an add-on module to existing SoTA DD methods.

Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary editing networks in the existing literature. In this work, we present our BoundaryDiffusion method for efficient, effective and light-weight semantic control with frozen pre-trained DDMs, without learning any extra networks. As one of the first learning-free diffusion editing works, we start by seeking a more comprehensive understanding of the intermediate high-dimensional latent spaces by theoretically and empirically analyzing their probabilistic and geometric behaviors in the Markov chain. We then propose to further explore the critical step in the denoising trajectory that characterizes the convergence of a pre-trained DDM and introduce an automatic search method. Last but not least, in contrast to the conventional understanding that DDMs have relatively poor semantic behaviors (in generic latent spaces), we prove that the critical latent space we found already forms semantic subspace boundaries at the generic level in unconditional DDMs, which allows us to do controllable manipulation by guiding the denoising trajectory towards the targeted boundary via a single-step operation. We conduct extensive experiments on multiple DPMs architectures (DDPM, iDDPM) and datasets (CelebA, CelebA-HQ, LSUN-church, LSUN-bedroom, AFHQ-dog) with different resolutions (64, 256), achieving superior or state-of-the-art performance in various task scenarios (image semantic editing, text-based editing, unconditional semantic control) to demonstrate the effectiveness.

Recently, due to the increasing requirements of medical imaging applications and the professional requirements of annotating medical images, few-shot learning has gained increasing attention in the medical image semantic segmentation field. To perform segmentation with limited number of labeled medical images, most existing studies use Prototypical Networks (PN) and have obtained compelling success. However, these approaches overlook the query imagefeatures extracted from the proposed representation network, failing to preserving the spatial connection between query and support images. In this paper, we propose a novel self-supervised few-shot medical image segmentation network and introduce a novel Cycle-Resemblance Attention (CRA) module to fully leverage the pixel-wise relation between query and support medical images. Notably, we first line up multiple attention blocks to refine more abundant relation information. Then, we present CRAPNet by integrating the CRA module with a classic prototype network, where pixel-wise relations between query and support features are well recaptured for segmentation. Extensive experiments on two different medical image datasets, e.g., abdomen MRI and abdomen CT, demonstrate the superiority of our model over existing state-of-the-art methods.

Forward symbolic execution is a powerful systematic software analysis technique, but suffers from the high cost of constraint solving. During symbolic execution, off-the-shelf constraint solvers are used to check the satisfiability of path conditions whenever they are updated. However, the satisfiability information is sufficient for path exploration, while the concrete solutions are needed only for special cases, e.g., when a property violation is detected. Thus, symbolic execution can be made more efficient by leveraging rapid constraint classification instead of time-consuming constraint solving when the concrete solutions are not necessary. This paper introduces ICON, a novel approach to scaling symbolic execution with intelligent constraint classification, where neural networks are utilized to classify path conditions for satisfiability. Experimental evaluation shows ICON is highly accurate in classifying path conditions, is faster than state-of-the-art techniques for conventional constraint solving, learning based constraint solving, and constraint solution reuse, and enables more efficient symbolic execution.

Video inpainting aims to utilize plausible contents to complete missing regions in the video. For different components, the reconstruction targets of missing regions are different,e.g.,smoothness preserving for flat regions, sharpening for edges and textures. Typically, existing methods treat the missing regions as a whole and holistically train the model by optimizing homogenous pixel-wise losses (e.g.,MSE). In this way, the trained models will be easily dominated and determined by flat regions, failing to infer realistic details (edges and textures) that are difficult to reconstruct but necessary for practical applications. In this paper, we propose a divide-and-conquer completion network for video inpainting. In particular, our network first uses discrete wavelet transform to decompose the deep features into low-frequency components containing structural information (flat regions) and high-frequency components involving detailed texture information. Thereafter, we feed these components into different branches and adopt the temporal attention feature aggregation module to generate missing contents, separately. It hence can realize flexible supervision utilizing the intermediate supervision learning strategy for each component, which has not been noticed and explored by current state-of-the-art video inpainting methods. Furthermore, we adopt a gradient-weighted reconstruction loss to supervise the completed frame reconstruction process, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed textures regions, making the model pay more attention to the complex detailed textures. Extensive experiments validate the superior performance of our divide-and-conquer model over state-of-the-art baselines in both quantitative and qualitative evaluations.

Deep Neural Networks (DNNs) have been proven to be vulnerable to poisoning attacks that poison the training data with a trigger pattern and thus manipulate the trained model to misclassify data instances. In this article, we study the poisoning attacks on video recognition models. We reveal the major limitations of the state-of-the-art poisoning attacks onstealthinessandattack effectiveness: (i) the frame-by-frame poisoning trigger may cause temporal inconsistency among the video frames which can be leveraged to easily detect the attack; (ii) the feature collision-based method for crafting poisoned videos could lack both generalization and transferability. To address these limitations, we propose a novel stealthy and efficient poisoning attack framework which has the following advantages: (i) we design a 3D poisoning trigger as natural-like textures, which can maintain temporal consistency and human-imperceptibility; (ii) we formulate an ensemble attack oracle as the optimization objective to craft poisoned videos, which could construct convex polytope-like adversarial subspaces in the feature space and thus gain more generalization; (iii) our poisoning attack can be readily extended to the black-box setting with good transferability. We have experimentally validated the effectiveness of our attack (e.g., up to$95\%$success rates with only less than$\sim 0.5\%$poisoned dataset).

In this paper, we tackle the problem of ground-view panorama image generation conditioning on top-view aerial image, which is a challenging problem due to large gap between image domains associated with different view-points. Instead of learning the underlying cross-view mapping by a feedforward network as previous methods, we propose a novel adversarial feedback GAN framework named PanoGAN consisting of two key components: an adversarial feedback module and a dual branch discrimination strategy. First, aerial image is fed into the generator to produce panorama image and segmentation map, which facilitates the use of semantic layout information for model training. Second, the discriminator's feature responses of model outputs are encoded by the adversarial feedback module and then fed back to the generator for the next round of generation. Continual improvement of generated image quality is achieved through an iterative generation process. Third, to pursue high-fidelity and semantic consistency of the generated panorama image, we propose a pixel-segmentation alignment mechanism under the dual branch discrimiantion strategy that promotes the cooperation between generator and discriminator. Extensive experimental results on two challenging cross-view image datasets show that the proposed PanoGAN generates high-quality panorama images with more convincing details than state-of-the-art methods. The source code and trained models are available at https://github.com/sswuai/PanoGAN.

Egocentric early action prediction aims to recognize actions from the first-person view by only observing a partial video segment, which is challenging due to the limited context information of the partial video. In this article, to tackle the egocentric early action prediction problem, we propose a novel multi-modal adversarial knowledge distillation framework. In particular, our approach involves a teacher network to learn the enhanced representation of the partial video by considering the future unobserved video segment, and a student network to mimic the teacher network to produce the powerful representation of the partial video and based on that predicting the action label. To promote the knowledge distillation between the teacher and the student network, we seamlessly integrate adversarial learning with latent and discriminative knowledge regularizations encouraging the learned representations of the partial video to be more informative and discriminative toward the action prediction. Finally, we devise a multi-modal fusion module toward comprehensively predicting the action label. Extensive experiments on two public egocentric datasets validate the superiority of our method over the state-of-the-art methods. We have released the codes and involved parameters to benefit other researchers. 1

Humans can easily recognize where and how the sound is produced via watching a scene and listening to corresponding audio cues. To achieve such cross-modal perception on machines, existing methods only use the maps generated by interpolation operations to localize the sound source. As semantic object-level localization is more attractive for potential practical applications, we argue that these existing map-based approaches only provide a coarse-grained and indirect description of the sound source. In this pa-per, we advocate a novel proposal-based paradigm that can directly perform semantic object-level localization, without any manual annotations. We incorporate the global re-sponse map as an unsupervised spatial constraint to weight the proposals according to how well they cover the esti-mated global shape of the sound source. As a result, our proposal-based sound source localization can be cast into a simpler Multiple Instance Learning (MIL) problem by filtering those instances corresponding to large sound-unrelated regions. Our method achieves state-of-the-art (SOTA) per-formance when compared to several baselines on multiple datasets.

Human activity recognition (HAR) based on multi-modal approach has been recently shown to improve the accuracy performance of HAR. However, restricted computational resources associated with wearable devices, i.e., smartwatch, failed to directly support such advanced methods. To tackle this issue, this study introduces an end-to-end Vision-to-Sensor Knowledge Distillation (VSKD) framework. In this VSKD framework, only time-series data, i.e., accelerometer data, is needed from wearable devices during the testing phase. Therefore, this framework will not only reduce the computational demands on wearable devices, but also produce a learning model that closely matches the performance of the computational expensive multi-modal approach. In order to retain the local temporal relationship and facilitate visual deep learning models, we first convert time-series data to two-dimensional images by applying the Gramian Angular Field (GAF) based encoding method. We adopted multi-scale TRN with BN-Inception and ResNet18 as the teacher and student network in this study, respectively. A novel loss function, named Distance and Angle-wised Semantic Knowledge loss (DASK), is proposed to mitigate the modality variations between the vision and the sensor domain. Extensive experimental results on UTD-MHAD, MMAct, and Berkeley-MHAD datasets demonstrate the competitiveness of the proposed VSKD model which can be deployed on wearable devices.

With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge devices, such as smartphones or tablets. However, optimal network pruning is a non-trivial task which mathematically is an NP-hard problem. Previous researchers explain training a pruned network as buying a lottery ticket. In this paper, we investigate the Magnitude-Based Pruning (MBP) scheme and analyze it from a novel perspective through Fourier analysis on the deep learning model to guide model designation. Besides explaining the generalization ability of MBP using Fourier transform, we also propose a novel two-stage pruning approach, where one stage is to obtain the topological structure of the pruned network and the other stage is to retrain the pruned network to recover the capacity using knowledge distillation from lower to higher on the frequency domain. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate the superiority of our novel Fourier analysis based MBP compared to other traditional MBP algorithms.

Place recognition or loop closure detection is one of the core components in a full SLAM system. In this paper, aiming at strengthening the relevancy of local neighboring points and the contextual dependency among global points simultaneously, we investigate the exploitation of transformer-based network for feature extraction, and propose a Hierarchical Transformer for Place Recognition (HiTPR). The HiTPR consists of four major parts: point cell generation, short-range transformer (SRT), long-range transformer (LRT) and global descriptor aggregation. Specifically, the point cloud is initially divided into a sequence of small cells by down-sampling and nearest neighbors searching. In the SRT, we extract the local feature for each point cell. While in the LRT, we build the global dependency among all of the point cells in the whole point cloud. Experiments on several standard benchmarks demonstrate the superiority of the HiTPR in terms of average recall rate, achieving 93.71 % at top 1 % and 86.63 % at top 1 on the Oxford RobotCar dataset for example.

The recent success of audio-visual representation learning can be largely attributed to their pervasive property of audio-visual synchronization, which can be used as self-annotated supervision. As a state-of-the-art solution, Audio-Visual Instance Discrimination (AVID) extends instance discrimination to the audio-visual realm. Existing AVID methods construct the contrastive set by random sampling based on the assumption that the audio and visual clips from all other videos are not semantically related. We argue that this assumption is rough, since the resulting contrastive sets have a large number of faulty negatives. In this paper, we overcome this limitation by proposing a novel Active Contrastive Set Mining (ACSM) that aims to mine the contrastive sets with informative and diverse negatives for robust AVID. Moreover, we also integrate a semantically-aware hard-sample mining strategy into our ACSM. The proposed ACSM is implemented into two most recent state-of-the-art AVID methods and significantly improves their performance. Extensive experiments conducted on both action and sound recognition on multiple datasets show the remarkably improved performance of our method.

Wearable sensor-based Human Action Recognition (HAR) has achieved remarkable success recently. However, the accuracy performance of wearable sensor-based HAR is still far behind the ones from the visual modalities-based system (i.e., RGB video, skeleton and depth). Diverse input modalities can provide complementary cues and thus improve the accuracy performance of HAR, but how to take advantage of multi-modal data on wearable sensor-based HAR has rarely been explored. Currently, wearable devices, i.e., smartwatches, can only capture limited kinds of non-visual modality data. This hinders the multi-modal HAR association as it is unable to simultaneously use both visual and non-visual modality data. Another major challenge lies in how to efficiently utilize multi-modal data on wearable devices with their limited computation resources. In this work, we propose a novel Progressive Skeleton-to-sensor Knowledge Distillation (PSKD) model which utilizes only time-series data, i.e., accelerometer data, from a smartwatch for solving the wearable sensor-based HAR problem. Specifically, we construct multiple teacher models using data from both teacher (human skeleton sequence) and student (time-series accelerometer data) modalities. In addition, we propose an effective progressive learning scheme to eliminate the performance gap between teacher and student models. We also designed a novel loss function called Adaptive-Confidence Semantic (ACS), to allow the student model to adaptively select either one of the teacher models or the ground-truth label it needs to mimic. To demonstrate the effectiveness of our proposed PSKD method, we conduct extensive experiments on Berkeley-MHAD, UTD-MHAD and MMAct datasets. The results confirm that the proposed PSKD method has competitive performance compared to the previous mono sensor-based HAR methods.

Cross-modal retrieval is an essential area of representation learning, which aims to retrieve instances with the same semantics from different modalities. In real implementation, a key challenge for cross-modal retrieval is to narrow the heterogeneity gap between different modalities and obtain modality-invariant and discriminative features. Typically, existing approaches for this task mainly learn inter-modal invariance and focus on how to combine pair-level loss and class-level loss, which cannot effectively and adequately learn discriminative features. To address these issues, in this paper, we propose a novel Cross-Modality Cross-Instance Contrastive Learning for Cross-Media Retrieval (C3CMR) method. Specifically, to fully employ the intra-modal similarities, we introduce the intra-modal contrastive learning to enhance the discriminative power of the unimodal features. Besides, we design a supervised inter-modal contrastive learning scheme to take full advantage of the label semantic associations. In this way, cross-semantic associations and inter-modal invariance can be further learned. Moreover, pertaining to the local suboptimal semantic similarity by only mining pairwise and triplewise sample relationships, we propose the cross-instance contrastive learning to mine the similarities among multiple instances. Comprehensive experimental results on four widely-used benchmark datasets demonstrate the superiority of our proposed method over several state-of-the-art cross-modal retrieval methods.

Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear gap exists in the current literature on evaluating the relative bias in the performance of multi-class classifiers. In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the class-wise bias of two models in comparison to one another. By evaluating the performance of these new metrics and by demonstrating their practical application, we show that they can be used to measure fairness as well as bias. These demonstrations show that our metrics can address specific needs for measuring bias in multi-class classification. Demonstration code is available at https://github.com/gentry-atkinson/CEV_SDE_demo.git.

Current vision and language tasks usually take complete visual data (e.g., raw images or videos) as input, however, practical scenarios may often consist the situations where part of the visual information becomes inaccessible due to various reasons e.g., restricted view with fixed camera or intentional vision block for security concerns. As a step towards the more practical application scenarios, we introduce a novel task that aims to describe a video using the natural language dialog between two agents as a supplementary information source given incomplete visual data. Different from most existing vision-language tasks where AI systems have full access to images or video clips, which may reveal sensitive information such as recognizable human faces or voices, we intentionally limit the visual input for AI systems and seek a more secure and transparent information medium, i.e., the natural language dialog, to supplement the missing visual information. Specifically, one of the intelligent agents - Q-BOT - is given two semantic segmented frames from the beginning and the end of the video, as well as a finite number of opportunities to ask relevant natural language questions before describing the unseen video. A-BOT, the other agent who has access to the entire video, assists Q-BOT to accomplish the goal by answering the asked questions. We introduce two different experimental settings with either a generative (i.e., agents generate questions and answers freely) or a discriminative (i.e., agents select the questions and answers from candidates) internal dialog generation process. With the proposed unified QA-Cooperative networks, we experimentally demonstrate the knowledge transfer process between the two dialog agents and the effectiveness of using the natural language dialog as a supplement for incomplete implicit visions.

Scene Graph Generation (SGG) aims to detect the objects and their pairwise predicates in an image. Existing SGG methods mainly fulfil the challenging predicate prediction task that involves severe long-tailed data distribution with a single classifier. However, we argue that this may be enough to differentiate predicates that present obvious differences (e.g.,$on$and$near$), but not sufficient to distinguish similar predicates that only have subtle differences (e.g.,$on$and$standing~on$). Towards this end, we divide the predicate prediction into a few sub-tasks with a Divide-and-Conquer Predictor (DC-Predictor). Specifically, we first develop an offline pattern-predicate correlation mining algorithm to discover the similar predicates that share the same object interaction pattern. Based on that, we devise a general pattern classifier and a set of specific predicate classifiers for DC-Predictor. The former works on recognizing the pattern of a given object pair and routing it to the corresponding specific predicate classifier, while the latter aims to differentiate similar predicates in each specific pattern. In addition, we introduce the Bayesian Personalized Ranking loss in each specific predicate classifier to enhance the pairwise differentiation between head predicates and their similar ones. Experiments on VG150 and GQA datasets show the superiority of our model over state-of-the-art methods.

This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze ( 256 ×256 ) and high-resolution CelebHQGaze ( 512 ×512 ). Second, we formulate the gaze correction task as an image inpainting problem, addressed using a Gaze Correction Module (GCM) and a Gaze Animation Module (GAM). Moreover, we propose an unsupervised training strategy, i.e., Synthesis-As-Training, to learn the correlation between the eye region features and the gaze angle. As a result, we can use the learned latent space for gaze animation with semantic interpolation in this space. Moreover, to alleviate both the memory and the computational costs in the training and the inference stage, we propose a Coarse-to-Fine Module (CFM) integrated with GCM and GAM. Extensive experiments validate the effectiveness of our method for both the gaze correction and the gaze animation tasks in both low and high-resolution face datasets in the wild and demonstrate the superiority of our method with respect to the state of the art.

Audio-visual matching aims to learn the intrinsic correspondence between image and audio clip. Existing works mainly concentrate on learning discriminative features, while ignore the cross-modal heterogeneous issue between audio and visual modalities. To deal with this issue, we propose a novel Adversarial-Metric Learning (AML) model for audio-visual matching. AML aims to generate a modality-independent representation for each person in each modality via adversarial learning, while simultaneously learns a robust similarity measure for cross-modality matching via metric learning. By integrating the discriminative modality-independent representation and robust cross-modality metric learning into an end-to-end trainable deep network, AML can overcome the heterogeneous issue with promising performance for audio-visual matching. Experiments on the various audio-visual learning tasks, including audio-visual matching, audio-visual verification and audio-visual retrieval on benchmark dataset demonstrate the effectiveness of the proposed AML model. The implementation codes are available onhttps://github.com/MLanHu/AML.

Action recognition has been a heated topic in computer vision for its wide application in vision systems. Previous approaches achieve improvement by fusing the modalities of the skeleton sequence and RGB video. However, such methods pose a dilemma between the accuracy and efficiency for the high complexity of the RGB video network. To solve the problem, we propose a multi-modality feature fusion network to combine the modalities of the skeleton sequence and RGB frame instead of the RGB video, as the key information contained by the combination of the skeleton sequence and RGB frame is close to that of the skeleton sequence and RGB video. In this way, complementary information is retained while the complexity is reduced by a large margin. To better explore the correspondence of the two modalities, a two-stage fusion framework is introduced in the network. In the early fusion stage, we introduce a skeleton attention module that projects the skeleton sequence on the single RGB frame to help the RGB frame focus on the limb movement regions. In the late fusion stage, we propose a cross-attention module to fuse the skeleton feature and the RGB feature by exploiting the correlation. Experiments on two benchmarks, NTU RGB+D and SYSU, show that the proposed model achieves competitive performance compared with the state-of-the-art methods while reducing the complexity of the network.

Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. While plausible facial details are predicted, the models tend to over-depend on local color appearance and suffer from ambiguous noise. To address such problem, this paper presents a novel Learning to Aggregate and Personalize (LAP) framework for unsupervised robust 3D face modeling. Instead of using controlled environment, the proposed method implicitly disentangles ID-consistent and scene-specific face from unconstrained photo set. Specifically, to learn ID-consistent face, LAP adaptively aggregates intrinsic face factors of an identity based on a novel curriculum learning approach with relaxed consistency loss. To adapt the face for a personalized scene, we propose a novel attribute-refining network to modify ID-consistent face with target attribute and details. Based on the proposed method, we make unsupervised 3D face modeling benefit from meaningful image facial structure and possibly higher resolutions. Extensive experiments on benchmarks show LAP recovers superior or competitive face shape and texture, compared with state-of-the-art (SOTA) methods with or without prior and supervision.

People can easily imagine the potential sound while seeing an event. This natural synchronization between audio and visual signals reveals their intrinsic correlations. To this end, we propose to learn the audio-visual correlations from the perspective of cross-modal generation in a self-supervised manner, the learned correlations can be then readily applied in multiple downstream tasks such as the audio-visual cross-modal localization and retrieval. We introduce a novel Variational AutoEncoder (VAE) framework that consists of Multiple encoders and a Shared decoder (MS-VAE) with an additional Wasserstein distance constraint to tackle the problem. Extensive experiments demonstrate that the optimized latent representation of the proposed MS-VAE can effectively learn the audio-visual correlations and can be readily applied in multiple audio-visual downstream tasks to achieve competitive performance even without any given label information during training.

Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods via delicately designing various types of knowledge, they overlook the functional properties of neural networks, which makes the process of applying those techniques to new tasks unreliable and non-trivial. To alleviate such problem, in this paper, we initially leverage Lipschitz continuity to better represent the functional characteristic of neural networks and guide the knowledge distillation process. In particular, we propose a novel Lipschitz Continuity Guided Knowledge Distillation framework to faithfully distill knowledge by minimizing the distance between two neural networks’ Lipschitz constants, which enables teacher networks to better regularize student networks and improve the corresponding performance. We derive an explainable approximation algorithm with an explicit theoretical derivation to address the NP-hard problem of calculating the Lipschitz constant. Experimental results have shown that our method outperforms other benchmarks over several knowledge distillation tasks (e.g., classification, segmentation and object detection) on CIFAR-100, ImageNet, and PASCAL VOC datasets. Our code is available at https://github.com/42Shawn/LONDON/tree/master.

Cross-view video synthesis task seeks to generate video sequences of one view from another dramatically different view. In this paper, we investigate the exocentric (third-person) view to egocentric (first-person) view video generation task. This is challenging because egocentric view sometimes is remarkably different from the exocentric view. Thus, transforming the appearances across the two different views is a non-trivial task. Particularly, we propose a novel Bi-directional Spatial Temporal Attention Fusion Generative Adversarial Network (STA-GAN) to learn both spatial and temporal information to generate egocentric video sequences from the exocentric view. The proposed STA-GAN consists of three parts: temporal branch, spatial branch, and attention fusion. First, the temporal and spatial branches generate a sequence of fake frames and their corresponding features. The fake frames are generated in both downstream and upstream directions for both temporal and spatial branches. Next, the generated four different fake frames and their corresponding features (spatial and temporal branches in two directions) are fed into a novel multi-generation attention fusion module to produce the final video sequence. Meanwhile, we also propose a novel temporal and spatial dual-discriminator for more robust network optimization. Extensive experiments on the Side2Ego and Top2Ego datasets show that the proposed STA-GAN significantly outperforms the existing methods.

The major challenge in audio-visual event localization task lies in how to fuse information from multiple modalities effectively. Recent works have shown that the attention mechanism is beneficial to the fusion process. In this paper, we propose a novel joint attention mechanism with multi-modal fusion methods for audio-visual event localization. Particularly, we present a concise yet valid architecture that effectively learns representations from multiple modalities in a joint manner. Initially, visual features are combined with auditory features and then turned into joint representations. Next, we make use of the joint representations to attend to visual features and auditory features, respectively. With the help of this joint co-attention, new visual and auditory features are produced, and thus both features can enjoy the mutually improved benefits from each other. It is worth noting that the joint co-attention unit is recursive meaning that it can be performed multiple times for obtaining better joint representations progressively. Extensive experiments on the public AVE dataset have shown that the proposed method achieves significantly better results than the state-of-the-art methods.

It is theoretically insufficient to construct a complete set of semantics in the real world using single-modality data. As a typical application of multi-modality perception, the audio-visual event localization task aims to match audio and visual components to identify the simultaneous events of interest. Although some recent methods have been proposed to deal with this task, they cannot handle the practical situation of temporal inconsistency that is widespread in the audio-visual scene. Inspired by the human system which automatically filters out event-unrelated information when performing multi-modality perception, we propose a discriminative cross-modality attention network to simulate such a process. Similar to human mechanism, our network can adaptively select "where" to attend, "when" to attend and "which" to attend for audio-visual event localization. In addition, to prevent our network from getting trivial solutions, a novel eigenvalue-based objective function is proposed to train the whole network to better fuse audio and visual signals, which can obtain discriminative and nonlinear multi-modality representation. In this way, even with large temporal inconsistency between audio and visual sequence, our network is able to adaptively select event-valuable information for audio-visual event localization. Furthermore, we systemically investigate three subtasks of audio-visual event localization, i.e., temporal localization, weakly-supervised spatial localization and cross-modality localization. The visualization results also help us better understand how our network works.

This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video. However, it is non-trivial since it requires not only the comprehensive understanding of the video and sentence query, but also the accurate semantic correspondence capture between them. Existing efforts are mainly centered on exploring the sequential relation among video clips and query words to reason the video and sentence query, neglecting the other intra-modal relations (e.g., semantic similarity among video clips and syntactic dependency among the query words). Towards this end, in this work, we propose a Multi-modal Interaction Graph Convolutional Network (MIGCN), which jointly explores the complex intra-modal relations and inter-modal interactions residing in the video and sentence query to facilitate the understanding and semantic correspondence capture of the video and sentence query. In addition, we devise an adaptive context-aware localization method, where the context information is taken into the candidate moments and the multi-scale fully connected layers are designed to rank and adjust the boundary of the generated coarse candidate moments with different lengths. Extensive experiments on Charades-STA and ActivityNet datasets demonstrate the promising performance and superior efficiency of our model.

Despite much research progress in image semantic segmentation, it remains challenging under adverse environmental conditions caused by imaging limitations of the visible spectrum, while thermal infrared cameras have several advantages over cameras for the visible spectrum, such as operating in total darkness, insensitive to illumination variations, robust to shadow effects, and strong ability to penetrate haze and smog. These advantages of thermal infrared cameras make the segmentation of semantic objects in day and night. In this article, we propose a novel network architecture, called edge-conditioned convolutional neural network (EC-CNN), for thermal image semantic segmentation. Particularly, we elaborately design a gated featurewise transform layer in EC-CNN to adaptively incorporate edge prior knowledge. The whole EC-CNN is end-to-end trained and can generate high-quality segmentation results with edge guidance. Meanwhile, we also introduce a new benchmark data set named "Segmenting Objects in Day And night" (SODA) for comprehensive evaluations in thermal image semantic segmentation. SODA contains over 7168 manually annotated and synthetically generated thermal images with 20 semantic region labels and from a broad range of viewpoints and scene complexities. Extensive experiments on SODA demonstrate the effectiveness of the proposed EC-CNN against state-of-the-art methods.

Deep neural networks (DNNs) have been extremely successful in solving many challenging AI tasks in natural language processing, speech recognition, and computer vision nowadays. However, DNNs are typically computation intensive, memory demanding, and power hungry, which significantly limits their usage on platforms with constrained resources. Therefore, a variety of compression techniques (e.g., quantization, pruning, and knowledge distillation) have been proposed to reduce the size and power consumption of DNNs. Blockwise knowledge distillation is one of the compression techniques that can effectively reduce the size of a highly complex DNN. However, it is not widely adopted due to its long training time. In this article, we propose a novel parallel blockwise distillation algorithm to accelerate the distillation process of sophisticated DNNs. Our algorithm leverages local information to conduct independent blockwise distillation, utilizes depthwise separable layers as the efficient replacement block architecture, and properly addresses limiting factors (e.g., dependency, synchronization, and load balancing) that affect parallelism. The experimental results running on an AMD server with four Geforce RTX 2080Ti GPUs show that our algorithm can achieve 3x speedup plus 19 percent energy savings on VGG distillation, and 3.5x speedup plus 29 percent energy savings on ResNet distillation, both with negligible accuracy loss. The speedup of ResNet distillation can be further improved to 3.87 when using four RTX6000 GPUs in a distributed cluster.

In human multi-modality perception systems, the benefits of integrating auditory and visual information are extensive as they provide plenty supplementary cues for understanding the events. Despite some recent methods proposed for such application, they cannot deal with practical conditions with temporal inconsistency. Inspired by human system which puts different focuses at specific locations, time segments and media while performing multi-modality perception, we provide an attention-based method to simulate such process. Similar to human mechanism, our network can adaptively select “where” to attend, “when” to attend and “which” to attend for audio-visual event localization. In this way, even with large temporal inconsistent between vision and audio, our network is able to adaptively trade information between different modalities and successfully achieve event localization. Our method achieves state-of-the-art performance on AVE (Audio-Visual Event) dataset collected in the real life. In addition, we also systemically investigate audio-visual event localization tasks. The visualization results also help us better understand how our model works.

In this paper, we address the task of semantic-guided scene generation. One open challenge widely observed in global image-level generation methods is the difficulty of generating small objects and detailed local texture. To tackle this issue, in this work we consider learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately constructs and learns sub-generators concentrating on the generation of different classes, and is able to provide more scene details. To learn more discriminative class-specific feature representations for the local generation, a novel classification module is also proposed. To combine the advantage of both global image-level and the local class-specific generation, a joint generation network is designed with an attention fusion module and a dual-discriminator structure embedded. Extensive experiments on two scene image generation tasks show superior generation performance of the proposed model. State-of-the-art results are established by large margins on both tasks and on challenging public benchmarks. The source code and trained models are available at https://github.com/Ha0Tang/LGGAN.

Online depth learning is the problem of consistently adapting a depth estimation model to handle a continuously changing environment. This problem is challenging due to the network easily overfits on the current environment and forgets its past experiences. To address such problem, this paper presents a novel Learning to Prevent Forgetting (LPF) method for online mono-depth adaptation to new target domains in unsupervised manner. Instead of updating the universal parameters, LPF learns adapter modules to efficiently adjust the feature representation and distribution without losing the pre-learned knowledge in online condition. Specifically, to adapt temporal-continuous depth patterns in videos, we introduce a novel meta-learning approach to learn adapter modules by combining online adaptation process into the learning objective. To further avoid overfitting, we propose a novel temporal-consistent regularization to harmonize the gradient descent procedure at each online learning step. Extensive evaluations on real-world datasets demonstrate that the proposed method, with very limited parameters, significantly improves the estimation quality.

Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate exocentric (third-person) view to egocentric (first-person) view image generation. This is a challenging task since egocentric view sometimes is remarkably different from exocentric view. Thus, transforming the appearances across the two views is a nontrivial task. To this end, we propose a novel Parallel Generative Adversarial Network (P-GAN) with a novel cross-cycle loss to learn the shared information for generating egocentric images from exocentric view. We also incorporate a novel contextual feature loss in the learning procedure to capture the contextual information in images. Extensive experiments on the Exo-Ego datasets [1] show that our model outperforms the state-of-the-art approaches.

One-shot video-based re-identification, which uses only one labeled tracklet for each identity, is challenging since the framework usually suffers misalignment and inefficient utilizing of unlabeled data. In this paper we propose a novel local-global progressive learning framework to overcome the limitations. To obtain robust features in a tracklet, we first design sub-networks to learn four discriminative part-based feature maps and one global feature map which is insensitive to misalignment. Then a novel adaptive loss is proposed to balance the part-based and global feature properly. To utilize unlabeled data, our framework gradually select most reliable pseudo-labeled tracklets to the training set for iterative training. Extensive experiments are conducted on two video-based Re-ID datasets, MARS and DukeMTMC-VideoReID. The mAP of our model outperforms the state-of-the-art methods by 20.8% on the DukeMTMC-VideoReID dataset.

Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 ° video analysis. However, the lack of 360 ° datasets in literature hinders the research in this field. To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360° Kinetic human activity video dataset (EgoK360). The EgoK360 dataset contains annotations of human activity with different sub-actions, e.g., activity Ping-Pong with four sub-actions which are pickup-ball, hit, bounce-ball and serve. To the best of our knowledge, EgoK360 is the first dataset in the domain of first-person activity recognition with a 360° environmental setup, which will facilitate the egocentric 360 ° video understanding. We provide experimental results and comprehensive analysis of variants of the two-stream network for 360 egocentric activity recognition. The EgoK360 dataset can be downloaded from https://egok360.github.io/.

Nowadays 360 video analysis has become a significant research topic in the field since the appearance of high-quality and low-cost 360 wearable devices. In this paper, we propose a novel LiteFlowNet360 architecture for 360 videos optical flow estimation. We design LiteFlowNet360 as a domain adaptation framework from perspective video domain to 360 video domain. We adapt it from simple kernel transformation techniques inspired by Kernel Transformer Network (KTN) to cope with inherent distortion in 360 videos caused by the sphere-to-plane projection. First, we apply an incremental transformation of convolution layers in feature pyramid network and show that further transformation in inference and regularization layers are not important, hence reducing the network growth in terms of size and computation cost. Second, we refine the network by training with augmented data in a supervised manner. We perform data augmentation by projecting the images in a sphere and re-projecting to a plane. Third, we train LiteFlowNet360 in a self-supervised manner using target domain 360 videos. Experimental results show the promising results of 360 video optical flow estimation using the proposed novel architecture.

Since we were babies, we intuitively develop the ability to correlate the input from different cognitive sensors such as vision, audio, and text. However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties. Previous works discover that there should be bridges among different modalities. From a neurology and psychology perspective, humans have the capacity to link one modality with another one, e.g., associating a picture of a bird with the only hearing of its singing and vice versa. Is it possible for machine learning algorithms to recover the scene given the audio signal? In this paper, we propose a novel Cascade Attention-Guided Residue GAN (CAR-GAN), aiming at reconstructing the scenes given the corresponding audio signals. Particularly, we present a residue module to mitigate the gap between different modalities progressively. Moreover, a cascade attention guided network with a novel classification loss function is designed to tackle the cross-modal learning task. Our model keeps consistency in the high-level semantic label domain and is able to balance two different modalities. The experimental results demonstrate that our model achieves the state-of-the-art cross-modal audio-visual generation on the challenging Sub-URMP dataset.

Person re-identification aims to identify the same person from different cameras, which needs to integrate whole-body information and capture global correlation. However, convolutional neural network is able to only capture short-distance information because of the size of filters. Self-attention is introduced to capture long-distance correlation, but inner-product similarity calculation in self-attention mingles semantic response and semantic difference together. Semantic difference is more important for person re-identification, because it is robust to illumination without the effect of semantic response. However, we find the scale of norms measuring semantic response is much larger than angle measuring semantic difference by decoupling inner-product similarity into norms and angle. To balance the importance of semantic response and semantic difference in self-attention, we propose the decoupled self-attention module for person re-identification to make the most of self-attention. Extensive experiments show that the decoupled self-attention module obtains significant performance with easier convergence and stronger robustness.

We address the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need of precise annotations of the gaze angle and the head pose. We created a new dataset called CelebAGaze consisting of two domains X, Y, where the eyes are either staring at the camera or somewhere else. Our method consists of three novel modules: the Gaze Correction module(GCM), the Gaze Animation module(GAM), and the Pretrained Autoencoder module (PAM). Specifically, GCM and GAM separately train a dual in-painting network using data from the domain X for gaze correction and data from the domain Y for gaze animation. Additionally, a Synthesis-As-Training method is proposed when training GAM to encourage the features encoded from the eye region to be correlated with the angle information, resulting in gaze animation achieved by interpolation in the latent space. To further preserve the identity information e.g., eye shape, iris color, we propose the PAM with an Autoencoder, which is based on Self-Supervised mirror learning where the bottleneck features are angle-invariant and which works as an extra input to the dual in-painting models. Extensive experiments validate the effectiveness of the proposed method for gaze correction and gaze animation in the wild and demonstrate the superiority of our approach in producing more compelling results than state-of-the-art baselines. Our code, the pretrained models and supplementary results are available at:https://github.com/zhangqianhui/GazeAnimation.

Unstructured neural network pruning is an effective technique that can significantly reduce theoretical model size, computation demand and energy consumption of large neural networks without compromising accuracy. However, a number of fundamental questions about pruning are not answered yet. For example, do the pruned neural networks contain the same representations as the original network? Is pruning a compression or evolution process? Does pruning only work on trained neural networks? What is the role and value of the uncovered sparsity structure? In this paper, we strive to answer these questions by analyzing three unstructured pruning methods (magnitude based pruning, post-pruning re-initialization, and random sparse initialization). We conduct extensive experiments using the Singular Vector Canonical Correlation Analysis (SVCCA) tool to study and contrast layer representations of pruned and original ResNet, VGG, and ConvNet models. We have several interesting observations: 1) Pruned neural network models evolve to substantially different representations while still maintaining similar accuracy. 2) Initialized sparse models can achieve reasonably good accuracy compared to well-engineered pruning methods. 3) Sparsity structures discovered by pruning models are not inherently important or useful.

Most person re-identification (re-ID) approaches are based on supervised learning, which requires intensive manual annotation for training data. However, it is not only resourceintensive to acquire identity annotation but also impractical to label the large-scale real-world data. To relieve this problem, we propose a bottom-up clustering (BUC) approach to jointly optimize a convolutional neural network (CNN) and the relationship among the individual samples. Our algorithm considers two fundamental facts in the re-ID task, i.e., diversity across different identities and similarity within the same identity. Specifically, our algorithm starts with regarding individual sample as a different identity, which maximizes the diversity over each identity. Then it gradually groups similar samples into one identity, which increases the similarity within each identity. We utilizes a diversity regularization term in the bottom-up clustering procedure to balance the data volume of each cluster. Finally, the model achieves an effective trade-off between the diversity and similarity. We conduct extensive experiments on the large-scale image and video re-ID datasets, including Market-1501, DukeMTMCreID, MARS and DukeMTMC-VideoReID. The experimental results demonstrate that our algorithm is not only superior to state-of-the-art unsupervised re-ID approaches, but also performs favorably than competing transfer learning and semi-supervised learning methods.

In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widely-spread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.

Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible to generate images of natural scenes in arbitrary viewpoints, based on an image of the scene and a novel semantic map. The proposed SelectionGAN explicitly utilizes the semantic information and consists of two stages. In the first stage, the condition image and the target semantic map are fed into a cycled semantic-guided generation network to produce initial coarse results. In the second stage, we refine the initial results by using a multi-channel attention selection mechanism. Moreover, uncertainty maps automatically learned from attentions are used to guide the pixel loss for better network optimization. Extensive experiments on Dayton, CVUSA and Ego2Top datasets show that our model is able to generate significantly better results than the state-of-the-art methods. The source code, data and trained models are available at https://github.com/Ha0Tang/SelectionGAN.

Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (W-net) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. To validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks.

In this paper, we investigate the audio-visual event localization problem. This task is to localize a visible and audible event in a video. Previous methods first divide a video into short segments, and then fuse visual and acoustic features at the segment level. The duration of these segments is usually short, making the visual and acoustic feature of each segment possibly not well aligned. Direct concatenation of the two features at the segment level can be vulnerable to a minor temporal misalignment of the two signals. We propose a Dual Attention Matching (DAM) module to cover a longer video duration for better high-level event information modeling, while the local temporal information is attained by the global cross-check mechanism. Our premise is that one should watch the whole video to understand the high-level event, while shorter segments should be checked in detail for localization. Specifically, the global feature of one modality queries the local feature in the other modality in a bi-directional way. With temporal co-occurrence encoded between auditory and visual signals, DAM can be readily applied in various audio-visual event localization tasks, e.g., cross-modality localization, supervised event localization. Experiments on the AVE dataset show our method outperforms the state-of-the-art by a large margin.

In this paper, we focus on the facial expression translation task and propose a novel Expression Conditional GAN (ECGAN) which can learn the mapping from one image domain to another one based on an additional expression attribute. The proposed ECGAN is a generic framework and is applicable to different expression generation tasks where specific facial expression can be easily controlled by the conditional attribute label. Besides, we introduce a novel face mask loss to reduce the influence of background changing. Moreover, we propose an entire framework for facial expression generation and recognition in the wild, which consists of two modules, i.e., generation and recognition. Finally, we evaluate our framework on several public face datasets in which the subjects have different races, illumination, occlusion, pose, color, content and background conditions. Even though these datasets are very diverse, both the qualitative and quantitative results demonstrate that our approach is able to generate facial expressions accurately and robustly.

Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure. Although the spectral clustering based methods achieve promotion in multi-view clustering, their utility is limited by the separate learning manner in which affinity matrix construction and cluster indicator estimation are isolated. In this paper, we propose to jointly learn the self-representation, continue and discrete cluster indicators in an unified model. Our model can explore the subspace structure of each view and fusion them to facilitate clustering simultaneously. Experimental results on two benchmark datasets demonstrate that our method outperforms other existing competitive multi-view clustering methods.

The state-of-the-art approaches in Generative Adversarial Networks (GANs) are able to learn a mapping function from one image domain to another with unpaired image data. However, these methods often produce artifacts and can only be able to convert low-level information, but fail to transfer high-level semantic part of images. The reason is mainly that generators do not have the ability to detect the most discriminative semantic part of images, which thus makes the generated images with low-quality. To handle the limitation, in this paper we propose a novel Attention-Guided Generative Adversarial Network (AGGAN), which can detect the most discriminative semantic object and minimize changes of unwanted part for semantic manipulation problems without using extra data and models. The attention-guided generators in AGGAN are able to produce attention masks via a built-in attention mechanism, and then fuse the input image with the attention mask to obtain a target image with high-quality. Moreover, we propose a novel attention-guided discriminator which only considers attended regions. The proposed AGGAN is trained by an end-to-end fashion with an adversarial loss, cycle-consistency loss, pixel loss and attention loss. Both qualitative and quantitative results demonstrate that our approach is effective to generate sharper and more accurate images than existing models.

In this work, we propose a novel Cycle In Cycle Generative Adversarial Network (C2GAN) for the task of keypoint-guided image generation. The proposed C2GAN is a cross-modal framework exploring a joint exploitation of the keypoint and the image data in an interactive manner. C2GAN contains two different types of generators, i.e., keypoint-oriented generator and image-oriented generator. Both of them are mutually connected in an end-to-end learnable fashion and explicitly form three cycled sub-networks, i.e., one image generation cycle and two keypoint generation cycles. Each cycle not only aims at reconstructing the input domain, and also produces useful output involving in the generation of another cycle. By so doing, the cycles constrain each other implicitly, which provides complementary information from the two different modalities and brings extra supervision across cycles, thus facilitating more robust optimization of the whole network. Extensive experimental results on two publicly available datasets, i.e., Radboud Faces and Market-1501, demonstrate that our approach is effective to generate more photo-realistic images compared with state-of-the-art models.

In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN). DDLCN has most of the standard deep learning layers (pooling, fully, connected, input/output, etc.) but the main difference is that the fundamental convolutional layers are replaced by novel compound dictionary learning and coding layers. The dictionary learning layer learns an over-complete dictionary for the input training data. At the deep coding layer, a locality constraint is added to guarantee that the activated dictionary bases are close to each other. Next, the activated dictionary atoms are assembled together and passed to the next compound dictionary learning and coding layers. In this way, the activated atoms in the first layer can be represented by the deeper atoms in the second dictionary. Intuitively, the second dictionary is designed to learn the fine-grained components which are shared among the input dictionary atoms. In this way, a more informative and discriminative low-level representation of the dictionary atoms can be obtained. We empirically compare the proposed DDLCN with several dictionary learning methods and deep learning architectures. The experimental results on four popular benchmark datasets demonstrate that the proposed DDLCN achieves competitive results compared with state-of-the-art approaches.

SUMMARY: This note describes nTracer, an ImageJ plug-in for user-guided, semi-automated tracing of multispectral fluorescent tissue samples. This approach allows for rapid and accurate reconstruction of whole cell morphology of large neuronal populations in densely labeled brains. AVAILABILITY AND IMPLEMENTATION: nTracer was written as a plug-in for the open source image processing software ImageJ. The software, instructional documentation, tutorial videos, sample image and sample tracing results are available at https://www.cai-lab.org/ntracer-tutorial. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Modeling the aging process of human faces is important for cross-age face verification and recognition. In this paper, we propose a Recurrent Face Aging (RFA) framework which takes as input a single image and automatically outputs a series of aged faces. The hidden units in the RFA are connected autoregressively allowing the framework to age the person by referring to the previous aged faces. Due to the lack of labeled face data of the same person captured in a long range of ages, traditional face aging models split the ages into discrete groups and learn a one-step face transformation for each pair of adjacent age groups. Since human face aging is a smooth progression, it is more appropriate to age the face by going through smooth transitional states. In this way, the intermediate aged faces between the age groups can be generated. Towards this target, we employ a recurrent neural network whose recurrent module is a hierarchical triple-layer gated recurrent unit which functions as an autoencoder. The bottom layer of the module encodes the input to a latent representation, and the top layer decodes the representation to a corresponding aged face. The experimental results demonstrate the effectiveness of our framework.

Hand gesture-to-gesture translation in the wild is a challenging task since hand gestures can have arbitrary poses, sizes, locations and self-occlusions. Therefore, this task requires a high-level understanding of the mapping between the input source gesture and the output target gesture. To tackle this problem, we propose a novel hand Gesture Generative Adversarial Network (GestureGAN). GestureGAN consists of a single generator G and a discriminator D, which takes as input a conditional hand image and a target hand skeleton image. GestureGAN utilizes the hand skeleton information explicitly, and learns the gesture-to-gesture mapping through two novel losses, the color loss and the cycle-consistency loss. The proposed color loss handles the issue of "channel pollution" while back-propagating the gradients. In addition, we present the Frechet ResNet Distance (FRD) to evaluate the quality of generated images. Extensive experiments on two widely used benchmark datasets demonstrate that the proposed GestureGAN achieves state-of-the-art performance on the unconstrained hand gesture-to-gesture translation task. Meanwhile, the generated images are in high-quality and are photo-realistic, allowing them to be used as data augmentation to improve the performance of a hand gesture classifier. Our model and code are available at https://github.com/Ha0Tang/GestureGAN.

The twelve papers in this special section focus on learning systems with shared information for computer vision and multimedia communication analysis. In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes containing a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with shared information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different levels of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems.

To benefit the skin care, this paper aims to design an automatic and effective visual analysis framework, with the expectation of recognizing the skin disease from a given image conveying the disease affected surface. This task is nontrivial, since it is hard to collect sufficient well-labeled samples. To address such problem, we present a novel transfer learning model, which is able to incorporate external knowledge obtained from the rich and relevant Web images contributed by grassroots. In particular, we first construct a target domain by crawling a small set of images from vertical and professional dermatological websites. We then construct a source domain by collecting a large set of skin disease related images from commercial search engines. To reinforce the learning performance in the target domain, we initially build a learning model in the target domain, and then seamlessly leverage the training samples in the source domain to enhance this learning model. The distribution gap between these two domains are bridged by a linear combination of Gaussian kernels. Instead of training models with low-level features, we resort to deep models to learn the succinct, invariant, and high-level image representations. Different from previous efforts that focus on a few types of skin diseases with a small and confidential set of images generated from hospitals, this paper targets at thousands of commonly seen skin diseases with publicly accessible Web images. Hence the proposed model is easily repeatable by other researchers and extendable to other disease types. Extensive experiments on a real-world dataset have demonstrated the superiority of our proposed method over the state-of-the-art competitors.

Graph-based dimensionality reduction techniques have been widely and successfully applied to clustering and classification tasks. The basis of these algorithms is the constructed graph which dictates their performance. In general, the graph is defined by the input affinity matrix. However, the affinity matrix derived from the data is sometimes suboptimal for dimension reduction as the data used are very noisy. To address this issue, we propose the projective unsupervised flexible embedding models with optimal graph (PUFE-OG). We build an optimal graph by adjusting the affinity matrix. To tackle the out-of-sample problem, we employ a linear regression term to learn a projection matrix. The optimal graph and the projection matrix are jointly learned by integrating the manifold regularizer and regression residual into a unified model. The experimental results on the public benchmark datasets demonstrate that the proposed PUFE-OG outperforms state-of-the-art methods.

Learning from very few samples is a challenge for machine learning tasks, such as text and image classification. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model/parameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm first learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few samples) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm.

No abstract available.

Fine-grained activity understanding in videos has attracted considerable recent attention with a shift from action classification to detailed actor and action understanding that provides compelling results for perceptual needs of cutting-edge autonomous systems. However, current methods for detailed understanding of actor and action have significant limitations: they require large amounts of finely labeled data, and they fail to capture any internal relationship among actors and actions. To address these issues, in this paper, we propose a novel, robust multi-task ranking model for weakly supervised actor-action segmentation where only video-level tags are given for training samples. Our model is able to share useful information among different actors and actions while learning a ranking matrix to select representative supervoxels for actors and actions respectively. Final segmentation results are generated by a conditional random field that considers various ranking scores for different video parts. Extensive experimental results on the Actor-Action Dataset (A2D) demonstrate that the proposed approach outperforms the state-of-the-art weakly supervised methods and performs as well as the top-performing fully supervised method.

Brain decoding has become a hot topic in many recent brain studies. In a typical neuroimaging experiment, participants are presented with different categories of stimuli while their concurrent brain activity is recorded. Then a classifier is trained on the features extracted from the recorded brain data to discriminate different target stimuli classes. It is a common practice to hypothesize that the stimulus-related information exists in the brain data if the decoder can accurately predict the target stimulus category. However, most of the neuroimaging studies suffer from few and noisy samples. These constraints affects the performance of such decoding systems. In order to cope with this limitation, a dictionary learning approach is used in this paper to transfer knowledge from the multimedia domain to the brain domain. We show that such cross-modal domain adaptation yields better performance of the learning algorithm in the brain domain. This is the first study in the direction of cross-modal adaptation by joint dictionary learning on multimedia and brain modality.

Community-based health services have risen as important online resources for resolving users health concerns. Despite the value, the gap between what health seekers with specific health needs and what busy physicians with specific attitudes and expertise can offer is being widened. To bridge this gap, we present a question routing scheme that is able to connect health seekers to the right physicians. In this scheme, we first bridge the expertise matching gap via a probabilistic fusion of the physician-expertise distribution and the expertise-question distribution. The distributions are calculated by hypergraph-based learning and kernel density estimation. We then measure physicians attitudes toward answering general questions from the perspectives of activity, responsibility, reputation, and willingness. At last, we adaptively fuse the expertise modeling and attitude modeling by considering the personal needs of the health seekers. Extensive experiments have been conducted on a real-world dataset to validate our proposed scheme.

We propose perceptually guided photo retargeting, which shrinks a photo by simulating a human's process of sequentially perceiving visually/semantically important regions in a photo. In particular, we first project the local features (graphlets in this paper) onto a semantic space, wherein visual cues such as global spatial layout and rough geometric context are exploited. Thereafter, a sparsity-constrained learning algorithm is derived to select semantically representative graphlets of a photo, and the selecting process can be interpreted by a path which simulates how a human actively perceives semantics in a photo. Furthermore, we learn the prior distribution of such active graphlet paths (AGPs) from training photos that are marked as esthetically pleasing by multiple users. The learned priors enforce the corresponding AGP of a retargeted photo to be maximally similar to those from the training photos. On top of the retargeting model, we further design an online learning scheme to incrementally update the model with new photos that are esthetically pleasing. The online update module makes the algorithm less dependent on the number and contents of the initial training data. Experimental results show that: 1) the proposed AGP is over 90% consistent with human gaze shifting path, as verified by the eye-tracking data, and 2) the retargeting algorithm outperforms its competitors significantly, as AGP is more indicative of photo esthetics than conventional saliency maps.

Quality assessment is an indispensable technique in a large body of media applications, i.e., photo retargeting, scenery rendering, and video summarization. In this paper, a fully automatic framework is proposed to mimic how humans subjectively perceive media quality. The key is a locality-preserved sparse encoding algorithm that accurately discovers human gaze shifting paths from each image or video clip. In particular, we first extract local image descriptors from each image/video, and subsequently project them into the so-called perceptual space. Then, a nonnegative matrix factorization (NMF) algorithm is proposed that represents each graphlet by a linear and sparse combination of the basis ones. Since each graphlet is visually/semantically similar to its neighbors, a locality-preserved constraint is encoded into the NMF algorithm. Mathematically, the saliency of each graphlet is quantified by the norm of its sparse codes. Afterward, we sequentially link them into a path to simulate human gaze allocation. Finally, a probabilistic quality model is learned based on such paths extracted from a collection of photos/videos, which are marked as high quality ones via multiple Flickr users. Comprehensive experiments have demonstrated that: 1) our quality model outperforms many of its competitors significantly, and 2) the learned paths are on average 89.5% consistent with real human gaze shifting paths.

People go to fortune tellers in hopes of learning things about their future. A future career path is one of the topics most frequently discussed. But rather than rely on "black arts" to make predictions, in this work we scientifically and systematically study the feasibility of career path prediction from social network data. In particular, we seamlessly fuse information from multiple social networks to comprehensively describe a user and characterize progressive properties of his or her career path. This is accomplished via a multi-source learning framework with fused lasso penalty, which jointly regularizes the source and career-stage relatedness. Extensive experiments on real-world data confirm the accuracy of our model.

Advanced computer vision and machine learning techniques tried to automatically categorize the emotions elicited by abstract paintings with limited success. Since the annotation of the emotional content is highly resourceconsuming, datasets of abstract paintings are either constrained in size or partially annotated. Consequently, it is natural to address the targeted task within a transductive framework. Intuitively, the use of multi-label classification techniques is desirable so to synergically exploit the relations between multiple latent variables, such as emotional content, technique, author, etc. A very popular approach for transductive multi-label recognition under linear classification settings is matrix completion. In this study we introduce non-linear matrix completion (NLMC), thus extending classical linear matrix completion techniques to the non-linear case. Together with the theory grounding the model, we propose an efficient optimization solver. As shown by our extensive experimental validation on two publicly available datasets, NLMC outperforms state-of-the-art methods when recognizing emotions from abstract paintings.

Modeling the aging process of human face is important for cross-age face verification and recognition. In this paper, we introduce a recurrent face aging (RFA) framework based on a recurrent neural network which can identify the ages of people from 0 to 80. Due to the lack of labeled face data of the same person captured in a long range of ages, traditional face aging models usually split the ages into discrete groups and learn a one-step face feature transformation for each pair of adjacent age groups. However, those methods neglect the in-between evolving states between the adjacent age groups and the synthesized faces often suffer from severe ghosting artifacts. Since human face aging is a smooth progression, it is more appropriate to age the face by going through smooth transition states. In this way, the ghosting artifacts can be effectively eliminated and the intermediate aged faces between two discrete age groups can also be obtained. Towards this target, we employ a twolayer gated recurrent unit as the basic recurrent module whose bottom layer encodes a young face to a latent representation and the top layer decodes the representation to a corresponding older face. The experimental results demonstrate our proposed RFA provides better aging faces over other state-of-the-art age progression methods.

Brain decoding (i.e., retrieving information from brain signals by employing machine learning algorithms) has recently received considerable attention across many communities. In a typical brain decoding paradigm, different types of stimuli are shown to the participant of the neuroimaging experiment, while his/her concurrent brain activity is captured using neuroimaging techniques. Then a machine learning algorithm is employed to categorize the measured brain signal into the target stimuli classes. Accurate prediction of the stimulus category by the algorithm is considered a positive evidence of the hypothesis of the existence of stimulus-related information in brain data. However, most of the brain decoding studies suffer from the constraint of having few and noisy samples. In order to overcome this limitation, in this paper, an adaptation paradigm is employed in order to transfer knowledge from visual domain to brain domain. We experimentally show that such adaptation procedure leads to improved results for the object recognition task in the brain domain, outperforming significantly the results achieved by the brain features alone. This is the first study in the direction of transferring knowledge by adapting representations learned on visual domain to the brain modality. We believe this paper opens up avenues for exploiting large-scale visual datasets to achieve performance gain in brain decoding.

Recently, head pose estimation (HPE) from low-resolution surveillance data has gained in importance. However, monocular and multi-view HPE approaches still work poorly under target motion, as facial appearance distorts owing to camera perspective and scale changes when a person moves around. To this end, we propose FEGA-MTL, a novel framework based on Multi-Task Learning (MTL) for classifying the head pose of a person who moves freely in an environment monitored by multiple, large field-of-view surveillance cameras. Upon partitioning the monitored scene into a dense uniform spatial grid, FEGA-MTL simultaneously clusters grid partitions into regions with similar facial appearance, while learning region-specific head pose classifiers. In the learning phase, guided by two graphs which a-priori model the similarity among (1) grid partitions based on camera geometry and (2) head pose classes, FEGA-MTL derives the optimal scene partitioning and associated pose classifiers. Upon determining the target's position using a person tracker at test time, the corresponding region-specific classifier is invoked for HPE. The FEGA-MTL framework naturally extends to a weakly supervised setting where the target's walking direction is employed as a proxy in lieu of head orientation. Experiments confirm that FEGA-MTL significantly outperforms competing single-task and multi-task learning methods in multi-view settings.

In multimedia annotation, due to the time constraints and the tediousness of manual tagging, it is quite common to utilize both tagged and untagged data to improve the performance of supervised learning when only limited tagged training data are available. This is often done by adding a geometry-based regularization term in the objective function of a supervised learning model. In this case, a similarity graph is indispensable to exploit the geometrical relationships among the training data points, and the graph construction scheme essentially determines the performance of these graph-based learning algorithms. However, most of the existing works construct the graph empirically and are usually based on a single feature without using the label information. In this paper, we propose a semi-supervised annotation approach by learning an optimized graph (OGL) from multi-cues (i.e., partial tags and multiple features), which can more accurately embed the relationships among the data points. Since OGL is a transductive method and cannot deal with novel data points, we further extend our model to address the out-of-sample issue. Extensive experiments on image and video annotation show the consistent superiority of OGL over the state-of-the-art methods.

Attributes, as mid-level features, have demonstrated great potential in visual recognition tasks due to their excellent propagation capability through different categories. However, existing attribute learning methods are prone to learning the correlated attributes. To discover the genuine attribute specific features, many feature selection methods have been proposed. However, these feature selection methods are implemented at the level of raw features that might be very noisy, and these methods usually fail to consider the structural information in the feature space. To address this issue, in this paper, we propose a label constrained dictionary learning approach combined with a multilayer filter. The feature selection is implemented at dictionary level, which can better preserve the structural information. The label constrained dictionary learning suppresses the intra-class noise by encouraging the sparse representations of intra-class samples to lie close to their center. A multilayer filter is developed to discover the representative and robust attribute specific bases. The attribute specific bases are only shared among the positive samples or the negative samples. The experiments on the challenging Animals with Attributes data set and the SUN attribute data set demonstrate the effectiveness of our proposed method.

With the popularity of mobile devices, photo retargeting has become a useful technique that adapts a high-resolution photo onto a low-resolution screen. Conventional approaches are limited in two aspects. The first factor is the de-emphasized role of semantic content that is many times more important than low-level features in photo aesthetics. Second is the importance of image spatial modeling: toward a semantically reasonable retargeted photo, the spatial distribution of objects within an image should be accurately learned. To solve these two problems, we propose a new semantically aware photo retargeting that shrinks a photo according to region semantics. The key technique is a mechanism transferring semantics of noisy image labels (inaccurate labels predicted by a learner like an SVM) into different image regions. In particular, we first project the local aesthetic features (graphlets in this work) onto a semantic space, wherein image labels are selectively encoded according to their noise level. Then, a category-sharing model is proposed to robustly discover the semantics of each image region. The model is motivated by the observation that the semantic distribution of graphlets from images tagged by a common label remains stable in the presence of noisy labels. Thereafter, a spatial pyramid is constructed to hierarchically encode the spatial layout of graphlet semantics. Based on this, a probabilistic model is proposed to enforce the spatial layout of a retargeted photo to be maximally similar to those from the training photos. Experimental results show that (1) noisy image labels predicted by different learners can improve the retargeting performance, according to both qualitative and quantitative analysis, and (2) the category-sharing model stays stable even when 32.36% of image labels are incorrectly predicted.

Complex event detection is a retrieval task with the goal of finding videos of a particular event in a large-scale unconstrained internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for the complex event detection task. However, how to effectively select the high-level semantic meaningful concepts from a large pool to assist complex event detection is rarely studied in the literature. In this paper, we propose two novel strategies to automatically select semantic meaningful concepts for the event detection task based on both the events-kit text descriptions and the concepts high-level feature descriptions. Moreover, we introduce a novel event oriented dictionary representation based on the selected semantic concepts. Towards this goal, we leverage training samples of selected concepts from the Semantic Indexing (SIN) dataset with a pool of 346 concepts, into a novel supervised multi-task dictionary learning framework. Extensive experimental results on TRECVID Multimedia Event Detection (MED) dataset demonstrate the efficacy of our proposed method.

We present a novel unsupervised deep learning framework for anomalous event detection in complex video scenes.While most existing works merely use hand-crafted appearance and motion features, we propose Appearance and Motion DeepNet (AMDN) which utilizes deep neural networks to automatically learn feature representations.To exploit the complementary information of both appearance and motion patterns, we introduce a novel double fusion framework, combining both the benefits of traditional early fusion and late fusion strategies.Specifically, stacked denoising autoencoders are proposed to separately learn both appearance and motion features as well as a joint representation (early fusion).Based on the learned representations, multiple one-class SVM models are used to predict the anomaly scores of each input, which are then integrated with a late fusion strategy for final anomaly detection.We evaluate the proposed method on two publicly available video surveillance datasets, showing competitive performance with respect to state of the art approaches.

In multimedia annotation, due to the time constraints and the tediousness of manual tagging, it is quite common to utilize both tagged and untagged data to improve the performance of supervised learning when only limited tagged training data are available. This is often done by adding a geometrically based regularization term in the objective function of a supervised learning model. In this case, a similarity graph is indispensable to exploit the geometrical relationships among the training data points, and the graph construction scheme essentially determines the performance of these graph-based learning algorithms. However, most of the existing works construct the graph empirically and are usually based on a single feature without using the label information. In this paper, we propose a semi-supervised annotation approach by learning an optimal graph (OGL) from multi-cues (i.e., partial tags and multiple features) which can more accurately embed the relationships among the data points. We further extend our model to address out-of-sample and noisy label issues. Extensive experiments on four public datasets show the consistent superiority of OGL over state-of-the-art methods by up to 12% in terms of mean average precision.

Image-based localization is an essential complement to GPS localization. Current image-based localization methods are based on either 2D-to-3D or 3D-to-2D to find the correspondences, which ignore the real scene geometric attributes. The main contribution of our paper is that we use a 3D model reconstructed by a short video as the query to realize 3D-to-3D localization under a multi-task point retrieval framework. Firstly, the use of a 3D model as the query enables us to efficiently select location candidates. Furthermore, the reconstruction of 3D model exploits the correlations among different images, based on the fact that images captured from different views for SfM share information through matching features. By exploring shared information (matching features) across multiple related tasks (images of the same scene captured from different views), the visual feature's view-invariance property can be improved in order to get to a higher point retrieval accuracy. More specifically, we use multi-task point retrieval framework to explore the relationship between descriptors and the 3D points, which extracts the discriminant points for more accurate 3D-to-3D correspondences retrieval. We further apply multi-task learning (MTL) retrieval approach on thermal images to prove that our MTL retrieval framework also provides superior performance for the thermal domain. This application is exceptionally helpful to cope with the localization problem in an environment with limited light sources.

We present PET- the Pascal animal classes Eye Tracking database. Our database comprises eye movement recordings compiled from forty users for the bird, cat, cow, dog, horse and sheep trainval sets from the VOC 2012 image set. Different from recent eye-tracking databases such as [1, 2], a salient aspect of PET is that it contains eye movements recorded for both the free-viewing and visual search task conditions. While some differences in terms of overall gaze behavior and scanning patterns are observed between the two conditions, a very similar number of fixations are observed on target objects for both conditions. As a utility application, we show how feature pooling around fixated locations enables enhanced (animal) object classification accuracy.

Attributes have shown great potential in visual recognition recently since they, as mid-level features, can be shared across different categories. However, existing attribute learning methods are prone to learning the correlated attributes which results in the difficulties of selecting attribute specific features. In this paper, we propose an attribute specific dictionary learning approach to address this issue. Category information is incorporated into our framework while learning the over-complete dictionary, which encourages the samples from the same category to have similar distributions over the dictionary bases. A novel scheme is developed to select the attribute specific dictionaries. The attribute specific dictionary consists of the bases which are only shared among the positive samples or the negative samples. The experiments on the Animals with Attributes (AwA) dataset show the effectiveness of our proposed method.

During natural social gatherings, humans tend to organize themselves in the so-called free-standing conversational groups. In this context, robust head and body pose estimates can facilitate the higher-level description of the ongoing interplay. Importantly, visual information typically obtained with a distributed camera network might not suffice to achieve the robustness sought. In this line of thought, recent advances in wearable sensing technology open the door to multimodal and richer information flows. In this paper we propose to cast the head and body pose estimation problem into a matrix completion task. We introduce a framework able to fuse multimodal data emanating from a combination of distributed and wearable sensors, taking into account the temporal consistency, the head/body coupling and the noise inherent to the scenario. We report results on the novel and challenging SALSA dataset, containing visual, auditory and infrared recordings of 18 people interacting in a regular indoor environment. We demonstrate the soundness of the proposed method and the usability for higher-level tasks such as the detection of F-formations and the discovery of social attention attractors.

Color plays an essential role in everyday life and is one of the most important visual cues in human perception. In abstract art, color is one of the essential means to convey the artist's intention and to affect the viewer emotionally. However, colors are rarely experienced in isolation, rather, they are usually presented together with other colors. In fact, the expressive properties of two-color combinations have been extensively studied by artists. It is intriguing to try to understand how color combinations in abstract paintings might affect the viewer emotionally, and to investigate if a computer algorithm can learn this mechanism.

There is an increasing interest in using hash codes for efficient multimedia retrieval and data storage. The hash functions are learned in such a way that the hash codes can preserve essential properties of the original space or the label information. Then the Hamming distance of the hash codes can approximate the data similarity. Existing works have demonstrated the success of many supervised hashing models. However, labeling data is time and labor consuming, especially for scalable datasets. In order to utilize the supervised hashing models to improve the discriminative power of hash codes, we propose a Supervised Hashing with Pseudo Labels (SHPL) which uses the cluster centers of the training data to generate pseudo labels, based on which the hash codes can be generated using the criteria of supervised hashing. More specifically, we utilize linear discriminant analysis (LDA) with trace ratio criterion as a showcase for hash functions learning and during the optimization, we prove that the pseudo labels and the hash codes can be jointly learned and iteratively updated in an unified framework. The learned hash functions can harness the discriminant power of trace ratio criterion, and thus can achieve better performance. Experimental results on three large-scale unlabeled datasets (i.e., SIFT1M, GIST1M, and SIFT1B) demonstrate the superior performance of our SHPL over existing hashing methods.

Recognizing human activities from videos is a fundamental research problem in computer vision. Recently, there has been a growing interest in analyzing human behavior from data collected with wearable cameras. First-person cameras continuously record several hours of their wearers' life. To cope with this vast amount of unlabeled and heterogeneous data, novel algorithmic solutions are required. In this paper, we propose a multitask clustering framework for activity of daily living analysis from visual data gathered from wearable cameras. Our intuition is that, even if the data are not annotated, it is possible to exploit the fact that the tasks of recognizing everyday activities of multiple individuals are related, since typically people perform the same actions in similar environments, e.g., people working in an office often read and write documents). In our framework, rather than clustering data from different users separately, we propose to look for clustering partitions which are coherent among related tasks. In particular, two novel multitask clustering algorithms, derived from a common optimization problem, are introduced. Our experimental evaluation, conducted both on synthetic data and on publicly available first-person vision data sets, shows that the proposed approach outperforms several single-task and multitask learning methods.

Complex event detection is a retrieval task with the goal of finding videos of a particular event in a large-scale unconstrained Internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for the complex event detection task. However, how to effectively select the high-level semantic meaningful concepts from a large pool to assist complex event detection is rarely studied in the literature. In this paper, we propose a novel strategy to automatically select semantic meaningful concepts for the event detection task based on both the events-kit text descriptions and the concepts high-level feature descriptions. Moreover, we introduce a novel event oriented dictionary representation based on the selected semantic concepts. Toward this goal, we leverage training images (frames) of selected concepts from the semantic indexing dataset with a pool of 346 concepts, into a novel supervised multitask lp -norm dictionary learning framework. Extensive experimental results on TRECVID multimedia event detection dataset demonstrate the efficacy of our proposed method.

The L1 -norm low-rank matrix factorization (LRMF) has been attracting much attention due to its wide applications to computer vision and pattern recognition. In this paper, we construct a new hierarchical Bayesian generative model for the L1 -norm LRMF problem and design a mean-field variational method to automatically infer all the parameters involved in the model by closed-form equations. The variational Bayesian inference in the proposed method can be understood as solving a weighted LRMF problem with different weights on matrix elements based on their significance and with L2 -regularization penalties on parameters. Throughout the inference process of our method, the weights imposed on the matrix elements can be adaptively fitted so that the adverse influence of noises and outliers embedded in data can be largely suppressed, and the parameters can be appropriately regularized so that the generalization capability of the problem can be statistically guaranteed. The robustness and the efficiency of the proposed method are substantiated by a series of synthetic and real data experiments, as compared with the state-of-the-art L1 -norm LRMF methods. Especially, attributed to the intrinsic generalization capability of the Bayesian methodology, our method can always predict better on the unobserved ground truth data than existing methods.

A robust gesture recognition system is an essential component in many human-computer interaction applications. In particular, the widespread adoption of portable devices and the diffusion of autonomous systems with limited power and load capacity has increased the need of developing efficient recognition algorithms which operates on video streams recorded from low cost devices and which can cope with the challenging issue of point of view changes. A further challenge arises as different users tend to perform the same gesture with different styles and speeds. Thus a classifier trained with gestures data of certain set of users may work poorly when data from other users are being processed. However, as often a mobile device or a robot are intended to be used by a single or by a small group of people, it would be desirable to have a gesture recognition system designed specifically for these users. In this paper we introduce a novel approach to face the problems of view-invariance and user personalization in the context of gesture interaction systems. More specifically, we propose a domain adaptation framework based on a feature space augmentation approach operating on robust view-invariant Self Similarity Matrix descriptors. To prove the effectiveness of our method a dataset corresponding to 17 users performing 10 different gestures under 3 point of views is collected and an extensive experimental evaluation is performed.

Sparse coding was shown to be able to find succinct representations of stimuli. Recently, it has been successfully applied to a variety of problems in image processing analysis. Sparse coding models data vectors as a linear combination of a few elements from a dictionary. However, most existing sparse coding methods are applied for a single task on a single dataset. The learned dictionary is then possibly biased towards the specific dataset and lacks of generalization abilities. In light of this, in this paper we propose a multitask sparse coding approach by uncovering a shared subspace among heterogeneous datasets. The proposed multi-task coding strategy leverages the commonality benefit from different datasets. Moreover, our multi-task coding framework is capable of direct classification by incorporating label information. Experimental results show that the dictionary learned by our approach has more generalization abilities and our model performs better classification compared to the model learned from only one dataset or the model learned from simply pooling different datasets together.

Motivated by applications in areas such as patient monitoring, tele-rehabilitation and ambient assisted living, analyzing activities of daily living is an active research topic in computer vision and image processing. In this paper we address the problem of everyday activity recognition from unlabeled data proposing a novel multi-task clustering (MTC) approach. Our intuition is that, when analyzing activities of daily living, we can take advantage of the fact that people tend to perform the same actions in the same environment (e.g. people working in an office environment use to read and write documents). Thus, even if labels are not available, information about typical activities can be exploited in the learning process. Arguing that the tasks of recognizing activities of specific individuals are related, we resort on multi-task learning and rather than clustering the data of each individual separately, we also look for clustering results which are coherent among related tasks. Extensive experimental results show that our method outperforms several state-of-the-art approaches by up to 11% on the Rochester activities of daily living dataset.

The widespread adoption of low-cost depth cameras has opened new opportunities to improve traditional action recognition systems. In this paper we focus on the specific problem of action recognition under view point changes and propose a novel approach for view-invariant action recognition operating jointly on visual data of color and depth camera channels. Our method is based on the unique combination of robust Self-Similarity Matrix (SSM) descriptors and multi-task learning. Indeed, multi-view action recognition is inherently a multi-task learning problem: images from a camera view can be modeled as visual data associated to the same task and it is reasonable to assume that the data of different tasks (camera views) are related to each other. In this work we propose a novel algorithm extending Multi-Task Linear Discriminant Analysis (MT-LDA) to enhance its flexibility by learning the dependencies between different views. Extensive experimental results on the publicly available ACT42dataset demonstrate the effectiveness of the proposed method.

Social attention behavior offers vital cues towards inferring one's personality traits from interactive settings such as round-table meetings and cocktail parties. Head orientation is typically employed as a proxy for determining the social attention direction when faces are captured at low-resolution. Recently, multi-task learning has been proposed to robustly compute head pose under perspective and scale-based facial appearance variations when multiple, distant and large field-of-view cameras are employed for visual analysis in smart-room applications. In this paper, we evaluate the effectiveness of an SVM-based MTL (SVM+MTL) framework with various facial descriptors (KL, HOG, LBP, etc.). The KL+HOG feature combination is found to produce the best classification performance, with SVM+MTL outperforming classical SVM irrespective of the feature used.

Multimedia event detection (MED) is a retrieval task with the goal of finding videos of a particular event in a large scale internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for MED. For most of events in MED, people are usually the central subjects in videos. The face of a person can be considered as the most important factor which brings a lot of information describing the video events. However, face information has not been systematically investigated in the previous research for MED. In this paper, we investigate the possibility of using the high-level face information to assist multimedia event detection. Moreover, since the labeled data in TRECVID MED dataset are limited, we propose a semi-supervised kernel ridge regression which works well in practice to explore the useful information from unlabeled data to assist the event detection. Extensive experimental results on TRECVID MED dataset show that our proposed method outperforms the state-of-the-art methods by up to 4%.

Nowadays, due to the exponential growth of the user generated videos and the prevailing videos sharing communities such as YouTube and Hulu, recognizing complex human activities in the wild becomes increasingly important in the research community. These videos are hard to study due to the frequent changes of camera viewpoint, multiple people moving in the scene, fast body movements, and varied lengths of video clips. In this paper, we propose a novel framework to analyze human interactions in TV shows. Firstly, we exploit the motion interchange pattern (MIP) to detect camera viewpoint changes in a video, and extract the salient motion points in the bounding box that covers the region of interest (ROI) in each frame. Then, we compute the large displacement optical flow for the salient pixels in the bounding box, and build the histogram of oriented optical flow as the motion feature vector for each frame. Finally, the self-similarity matrix (SSM) is adopted to capture the global temporal correlation of frames in a video. After extracting the SSM descriptors, the video feature vector can be constructed through different encoding approaches. The proposed framework works well in practice for unconstrained videos. We validate our approach on the TV human interaction (TVHI) dataset, and the experimental results demonstrate the efficacy of our strategy.

Robust action recognition under viewpoint changes has received considerable attention recently. To this end, self-similarity matrices (SSMs) have been found to be effective view-invariant action descriptors. To enhance the performance of SSM-based methods, we propose multitask linear discriminant analysis (LDA), a novel multitask learning framework for multiview action recognition that allows for the sharing of discriminative SSM features among different views (i.e., tasks). Inspired by the mathematical connection between multivariate linear regression and LDA, we model multitask multiclass LDA as a single optimization problem by choosing an appropriate class indicator matrix. In particular, we propose two variants of graph-guided multitask LDA: 1) where the graph weights specifying view dependencies are fixed a priori and 2) where graph weights are flexibly learnt from the training data. We evaluate the proposed methods extensively on multiview RGB and RGBD video data sets, and experimental results confirm that the proposed approaches compare favorably with the state-of-the-art.

We propose a novel Multi-Task Learning framework (FEGA-MTL) for classifying the head pose of a person who moves freely in an environment monitored by multiple, large field-of-view surveillance cameras. As the target (person) moves, distortions in facial appearance owing to camera perspective and scale severely impede performance of traditional head pose classification methods. FEGA-MTL operates on a dense uniform spatial grid and learns appearance relationships across partitions as well as partition-specific appearance variations for a given head pose to build region-specific classifiers. Guided by two graphs which a-priori model appearance similarity among (i) grid partitions based on camera geometry and (ii) head pose classes, the learner efficiently clusters appearance wise related grid partitions to derive the optimal partitioning. For pose classification, upon determining the target's position using a person tracker, the appropriate region specific classifier is invoked. Experiments confirm that FEGA-MTL achieves state-of-the-art classification with few training data.

Action recognition is a central problem in many practical applications, such as video annotation, video surveillance and human-computer interaction. Most action recognition approaches are currently based on localized spatio-temporal features that can vary significantly when the viewpoint changes. Therefore, the performance rapidly drops when training and test data correspond to different cameras/viewpoints. Recently, Self-Similarity Matrix (SSM) features have been introduced to circumvent this problem. To improve the performance of current SSM-based methods, in this paper we propose a multi-task learning framework for multi-view action recognition where discriminative SSM features are shared among different views. Inspired by the mathematical connection between multivariate linear regression and Linear Discriminant Analysis (LDA), we propose a novel learning algorithm, where a single optimization framework is defined for multi-task multi-class LDA by choosing an appropriate class indicator matrix. Experimental results on the popular IXMAS dataset demonstrate that our approach achieves accurate performance and compares favorably with state-of-the-art methods.

Correlates between social attention and personality traits have been widely acknowledged in social psychology studies. Head pose has commonly been employed as a proxy for determining the social attention direction in small group interactions. However, the impact of head pose estimation errors on personality estimates has not been studied to our knowledge.

The selection of discriminative features is an important and effective technique for many multimedia tasks. Using irrelevant features in classification or clustering tasks could deteriorate the performance. Thus, designing efficient feature selection algorithms to remove the irrelevant features is a possible way to improve the classification or clustering performance. With the successful usage of sparse models in image and video classification and understanding, imposing structural sparsity in \emph{feature selection} has been widely investigated during the past years. Motivated by the merit of sparse models, we propose a novel feature selection method using a sparse model in this paper. Different from the state of the art, our method is built upon $\ell _{2,p}$-norm and simultaneously considers both the global and local (GLocal) structures of data distribution. Our method is more flexible in selecting the discriminating features as it is able to control the degree of sparseness. Moreover, considering both global and local structures of data distribution makes our feature selection process more effective. An efficient algorithm is proposed to solve the $\ell_{2,p}$-norm sparsity optimization problem in this paper. Experimental results performed on real-world image and video datasets show the effectiveness of our feature selection method compared to several state-of-the-art methods.