Yuwei Zhang, Wenhao Yu, Shangbin Feng, Yifan Zhu, Letian Peng, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

We tackle the problem of quantifying the number of objects by a generative text-to-image model. Rather than retraining such a model for each new image domain of interest, which leads to high computational costs and limited scalability, we are the first to consider this problem from a domain-agnostic perspective. We propose QUOTA, an optimization framework for text-to-image models that enables effective object quantification across unseen domains without retraining. It leverages a dual-loop meta-learning strategy to optimize a domain-invariant prompt. Further, by integrating prompt learning with learnable counting and domain tokens, our method captures stylistic variations and maintains accuracy, even for object classes not encountered during training. For evaluation, we adopt a new benchmark QUANT-Bench specifically designed for object quantification in domain generalization, enabling rigorous assessment of object quantification accuracy and adaptability across unseen domains in text-to-image generation. Extensive experiments demonstrate that QUOTA outperforms conventional models in both object quantification accuracy and semantic consistency, setting a new benchmark for efficient and scalable text-to-image generation for any domain.

Developing grounding techniques for LLMs poses two requirements for interactive environments, i.e., (i) the presence of rich knowledge beyond the scope of existing LLMs and (ii) the complexity of tasks that require strategic reasoning. Existing environments fail to meet both requirements due to their simplicity or reliance on commonsense knowledge already encoded in LLMs for interaction. In this article, we present PokéLLMon, a new benchmark enriched with fictional game knowledge and characterized by the intense, dynamic, and adversarial gameplay of Pokémon battles, setting new challenges for the development of grounding and reasoning techniques in interactive environments. Empirical evaluations demonstrate that existing LLMs lack game knowledge and struggle in Pokémon battles. We investigate grounding techniques that leverage feedback and game knowledge, and provide a thorough analysis of reasoning methods from a new perspective of action consistency. Additionally, we introduce higher-level reasoning challenges when playing against human players. The implementation of our benchmark is released at: https://github.com/git-disl/PokeLLMon .

We introduce UniMuMo, a unified multimodal model capable of taking arbitrary text, music, and motion data as input conditions to generate outputs across all three modalities. To address the lack of time-synchronized data, we align unpaired music and motion data based on rhythmic patterns to leverage existing large-scale music-only and motion-only datasets. By converting music, motion, and text into token-based representation, our model bridges these modalities through a unified encoder-decoder transformer architecture. To support multiple generation tasks within a single framework, we introduce several architectural improvements. We propose encoding motion with a music codebook, mapping motion into the same feature space as music. We introduce a music-motion parallel generation scheme that unifies all music and motion generation tasks into a single transformer decoder architecture with a single training task of music-motion joint generation. Moreover, the model is designed by fine-tuning existing pre-trained single-modality models, significantly reducing computational demands. Extensive experiments demonstrate that UniMuMo achieves competitive results on all unidirectional generation benchmarks across music, motion, and text modalities.

Recent advancements in LLMs unlearning have shown remarkable success in removing unwanted data-model influences while preserving the model’s utility for legitimate knowledge. Despite these strides, sparse Mixture-of-Experts (MoE) LLMs–a key subset of the LLM family–have remained unexplored in the context of unlearning. As MoE LLMs are celebrated for their exceptional performance, we ask:How can unlearning be performed effectively and efficiently on MoE LLMs? Our pilot study shows that the dynamic routing nature of MoE LLMs introduces unique challenges, leading to excessive forgetting, uncontrolled knowledge erasure and substantial utility drops when existing unlearning methods are applied. To address this, we propose a novel Selected-Expert Unlearning Framework (SEUF). Through expert attribution, unlearning is concentrated on the most actively engaged experts for the specified knowledge. Concurrently, an anchor loss is applied to the router to stabilize the active state of this targeted expert, ensuring focused and controlled unlearning. SEUF is compatible with various standard unlearning algorithms. Extensive experiments demonstrate that SEUF enhances both forget quality up to 5% and model utility by 35% on MoE LLMs across various benchmarks and LLM architectures (compared to standard unlearning algorithms), while only unlearning 0.06% of the model parameters.

Attribute detection is crucial for many computer vision tasks, as it enables systems to describe properties such as color, texture, and material. Current approaches often rely on labor-intensive annotation processes which are inherently limited: objects can be described at an arbitrary level of detail (e.g., color vs. color shades), leading to ambiguities when the annotators are not instructed carefully. Furthermore, they operate within a predefined set of attributes, reducing scalability and adaptability to unforeseen downstream applications. We present Compositional Caching (ComCa), a training-free method for open-vocabulary attribute detection that overcomes these constraints. ComCa requires only the list of target attributes and objects as input, using them to populate an auxiliary cache of images by leveraging web-scale databases and Large Language Models to determine attribute-object compatibility. To account for the compositional nature of attributes, cache images receive soft attribute labels. Those are aggregated at inference time based on the similarity between the input and cache images, refining the predictions of underlying Vision-Language Models (VLMs). Importantly, our approach is model-agnostic, compatible with various VLMs. Experiments on public datasets demonstrate that ComCa significantly outperforms zero-shot and cache-based baselines, competing with recent training-based methods, proving that a carefully designed training-free approach can successfully address open-vocabulary attribute detection.

Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a single image, resulting in suboptimal performance when transferring knowledge from a LiDARbased teacher model to a camera-based student model. To facilitate effective distillation, we introduce Monocular Teaching Assistant Knowledge Distillation (MonoTAKD), which proposes a camera-based teaching assistant (TA) model to transfer robust 3D visual knowledge to the student model, leveraging the smaller feature representation gap. Additionally, we define 3D spatial cues as residual features that capture the differences between the teacher and the TA models. We then leverage these cues to improve the student model's 3D perception capabilities. Experimental results show that our MonoTAKD achieves state-of-the-art performance on the KITTI3D dataset. Furthermore, we evaluate the performance on nuScenes and KITTI raw datasets to demonstrate the generalization of our model to multi-view 3D and unsupervised data settings. Our code is available at https://github.com/hoiliu-0801/MonoTAKD.

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.

Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they often inherit harmful or unwanted knowledge from noisy internet-sourced datasets, compromising their reliability in real-world applications. Existing model unlearning methods either rely on access to pre-trained datasets or focus on coarse-grained unlearning (e.g., entire classes), leaving a critical gap for fine-grained unlearning. In this paper, we address the challenging scenario of selectively forgetting specific portions of knowledge within a class—without access to pre-trained data—while preserving the model’s overall performance. We propose a novel three-stage approach that progressively unlearns targeted knowledge while mitigating over-forgetting. It consists of (1) a forgetting stage to fine-tune the CLIP on samples to be forgotten, (2) a reminding stage to restore performance on retained samples, and (3) a restoring stage to recover zero-shot capabilities using model souping. Additionally, we introduce knowledge distillation to handle the distribution disparity between forgetting/retaining samples and unseen pre-trained data. Extensive experiments on CIFAR-10, ImageNet-1K, and style datasets demonstrate that our approach effectively unlearns specific subgroups while maintaining strong zero-shot performance on semantically similar subgroups and other categories, significantly outperforming baseline unlearning methods, which lose effectiveness under the CLIP unlearning setting.

Quantum machine learning, crucial in the noisy intermediate-scale quantum (NISQ) era, confronts challenges in error mitigation. Current noise-aware training (NAT) methods often assume static error rates in quantum neural networks (QNNs), overlooking the dynamic nature of quantum noise. Our work highlights how error rates fluctuate over time and across different qubits, affecting QNN performance even when overall error rates are similar. We introduce a novel NAT strategy that dynamically adjusts to standard and fatal error conditions, incorporating a low-complexity search method to identify fatal errors during optimization. This strategy significantly improves robustness, maintaining competitive performance with leading NAT methods across varying error scenarios.

Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks.However, they pose great safety risks against harmful queries and adversarial attacks.While recent mainstream safety efforts on LRMs, supervised fine-tuning (SFT), improve safety performance, we find that SFT-aligned models struggle to generalize to unseen jailbreak prompts.After thorough investigation of LRMs' generation, we identify a safety aha moment that can activate safety reasoning and lead to a safe response.This aha moment typically appears in the 'key sentence', which follows models' query understanding process and can indicate whether the model will proceed safely.Based on these insights, we propose SafeKey, including two complementary objectives to better activate the safety aha moment in the key sentence: (1) a Dual-Path Safety Head to enhance the safety signal in the model's internal representations before the key sentence, and (2) a Query-Mask Modeling objective to improve the models' attention on its query understanding, which has important safety hints.Experiments across multiple safety benchmarks demonstrate that our methods significantly improve safety generalization to a wide range of jailbreak attacks and out-of-distribution harmful prompts, lowering the average harmfulness rate by 9.6%, while maintaining general abilities.Our analysis reveals how SafeKey enhances safety by reshaping internal attention and improving the quality of hidden representations.

Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still falling behind with a typical success rate of 30%-50% on challenging benchmarks. Previous studies on fine-tuning MLLMs with synthetic charts are often restricted by their inadequate similarity to the real charts, which could compromise model training and performance on complex real-world charts. In this study, we show that modularizing chart generation and diversifying visual details improves chart understanding capabilities. In particular, we design a five-step data synthesis pipeline, where we separate data and function creation for single plot generation, condition the generation of later subplots on earlier ones for multi-subplot figures, visually diversify the generated figures, filter out low quality data, and finally generate the question-answer (QA) pairs with GPT-4o. This approach allows us to streamline the generation of fine-tuning datasets and introduce the effective chart dataset (ECD), which contains 10k+ chart images and 300k+ QA pairs, covering 25 topics and featuring 250+ chart type combinations with high visual complexity. We show that ECD consistently improves the performance of various MLLMs on a range of real-world and synthetic test sets. Code, data and models are available at: https://github.com/yuweiyang-anu/ECD.

Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations. GCP typically performs classification of the covariance matrices by applying matrix function normalization, such as matrix logarithm or power, followed by a Euclidean classifier. However, covariance matrices inherently lie in a Riemannian manifold, known as the Symmetric Positive Definite (SPD) manifold. The current literature does not provide a satisfactory explanation of why Euclidean classifiers can be applied directly to Riemannian features after the normalization of the matrix power. To mitigate this gap, this paper provides a comprehensive and unified understanding of the matrix logarithm and power from a Riemannian geometry perspective. The underlying mechanism of matrix functions in GCP is interpreted from two perspectives: one based on tangent classifiers (Euclidean classifiers on the tangent space) and the other based on Riemannian classifiers. Via theoretical analysis and empirical validation through extensive experiments on fine-grained and large-scale visual classification datasets, we conclude that the working mechanism of the matrix functions should be attributed to the Riemannian classifiers they implicitly respect. The code is available at https://github.com/GitZH-Chen/RiemGCP.git.

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the underlying data distribution. Unfortunately, existing methods require model fine-tuning with distillation losses to encourage diversity and representativeness. However, these methods do not guarantee sample diversity, limiting their performance. We propose a mode-guided diffusion model leveraging a pre-trained diffusion model without the need to fine-tune with distillation losses. Our approach addresses dataset diversity in three stages: Mode Discovery to identify distinct data modes, Mode Guidance to enhance intra-class diversity, and Stop Guidance to mitigate artifacts in synthetic samples that affect performance. We evaluate our approach on ImageNette, ImageIDC, ImageNet-100, and ImageNet-1K, achieving accuracy improvements of 4.4%, 2.9%, 1.6%, and 1.6%, respectively, over state-of-the-art methods. Our method eliminates the need for fine-tuning diffusion models with distillation losses, significantly reducing computational costs.

Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for downstream tasks often involves nested bilevel structures, such as tuning hyperparameters for fine-tuning tasks or noise schedules in training dynamics, where traditional bilevel methods fail due to the infinite-dimensional probability space and prohibitive sampling costs. We formalize this challenge as a generative bilevel optimization problem and address two key scenarios: (1) fine-tuning pre-trained models via an inference-only lower-level solver paired with a sample-efficient gradient estimator for the upper level, and (2) training diffusion model from scratch with noise schedule optimization by reparameterizing the lower-level problem and designing a computationally tractable gradient estimator. Our first-order bilevel framework overcomes the incompatibility of conventional bilevel methods with diffusion processes, offering theoretical grounding and computational practicality. Experiments demonstrate that our method outperforms existing fine-tuning and hyperparameter search baselines.

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.

Designing egocentric 3D hand pose estimation systems that can perform reliably in complex, real-world scenarios is crucial for downstream applications. Previous approaches using RGB or NIR imagery struggle in challenging conditions: RGB methods are susceptible to lighting variations and obstructions like handwear, while NIR techniques can be disrupted by sunlight or interference from other NIR-equipped devices. To address these limitations, we present ThermoHands, the first benchmark focused on thermal image-based egocentric 3D hand pose estimation, demonstrating the potential of thermal imaging to achieve robust performance under these conditions. The benchmark includes a multi-view and multi-spectral dataset collected from 28 subjects performing hand-object and hand-virtual interactions under diverse scenarios, accurately annotated with 3D hand poses through an automated process. We introduce a new baseline method, TherFormer, utilizing dual transformer modules for effective egocentric 3D hand pose estimation in thermal imagery. Our experimental results highlight TherFormer's leading performance and affirm thermal imaging's effectiveness in enabling robust 3D hand pose estimation in adverse conditions.

This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens with small accuracy degradation. However these methods are not designed with edge device deployment in mind: they do not leverage information about the latency-workload trends to improve efficiency. We address this shortcoming in our work. First we identify factors that affect ViT latency-workload relationships. Second we determine token pruning schedule by leveraging non-linear latency-workload relationships. Third we demonstrate a training-free token pruning method utilizing this schedule. We show other methods may increase latency by 2-30% while we reduce latency by 9-26%. For similar latency (within 5.2% or 7ms) across devices we achieve 78.6%-84.5% ImageNet1K classification accuracy while the state-of-the-art Token Merging achieves 45.8%-85.4%.

Recently, generative models such as diffusion models (DMs) have gained prominence in various applications, and there is a growing demand for their deployment on resource-constrained devices. Model pruning provides an effective solution by reducing the model redundancy without significantly impacting performance. However, most existing model pruning methods are designed for classification models and often lead to substantial performance degradation when applied to generative models. To address this issue, we propose Comp-Diff, a novel two-stage framework of pruning and knowledge distillation tailored for diffusion models. In the pruning stage, we propose a new structured content-aware pruning (CaP) method within Comp-Diff to identify and preserve informative units (filters/channels) that actually contribute to the generative capability of the model. Specifically, we introduce input perturbations to the pre-trained model and measure each unit’s importance score using gradients induced by these perturbations. Units with higher importance scores are considered more informative and are retained to maintain the model’s generative power. In the fine-tuning stage of Comp-Diff, we propose the distribution-aware knowledge distillation (DaKD) method, which effectively transfers fine-grained knowledge from the original model to the pruned one on both attention and noise distribution levels. In addition, DaKD includes an adversarial loss to improve the quality and diversity of generated outputs. To verify and evaluate our method, we apply the proposed Comp-Diff on three representative tasks: unconditional image generation, conditional image generation, and text-to-image generation. Extensive experiments on both multi-step and one-step diffusion models demonstrate that the proposed framework consistently yields compact models and outperforms existing pruning techniques by a large margin.

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.

Letian Peng, Yuwei Zhang, Zilong Wang, Jayanth Srinivasa, Gaowen Liu, Zihan Wang, Jingbo Shang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Deep neural networks for learning Symmetric Positive Definite (SPD) matrices are gaining increasing attention in machine learning. Despite the significant progress, most existing SPD networks use traditional Euclidean classifiers on an approximated space rather than intrinsic classifiers that accurately capture the geometry of SPD manifolds. In-spired by Hyperbolic Neural Networks (HNNs), we propose Riemannian Multinomial Logistics Regression (RMLR) for the classification layers in SPD networks. We introduce a unified framework for building Riemannian classifiers under the metrics pulled back from the Euclidean space, and showcase our framework under the parameterized Log-Euclidean Metric (LEM) and Log-Cholesky Metric (LCM). Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks. The effectiveness of our method is demonstrated in three applications: radar recognition, human action recognition, and electroencephalography (EEG) classification. The code is available at https://github.com/GitZH-Chen/SPDMLR.git.

While excellent in transfer learning, Vision-Language models (VLMs) come with high computational costs due to their large number of parameters. To address this issue, removing parameters via model pruning is a viable solution. However, existing techniques for VLMs are task-specific, and thus require pruning the network from scratch for each new task of interest. In this work, we explore a new direction: Task-Agnostic Vision-Language Pruning (TA-VLP). Given a pretrained VLM, the goal is to find a unique pruned counterpart transferable to multiple unknown downstream tasks. In this challenging setting, the transferable representations already encoded in the pretrained model are a key aspect to preserve. Thus, we propose Multimodal Flow Pruning (MULTIFLOW), a first, gradient-free, pruning framework for TA-VLP where: (i) the importance of a parameter is expressed in terms of its magnitude and its information flow, by incorporating the saliency of the neurons it connects; and (ii) pruning is driven by the emergent (multimodal) distribution of the VLM parameters after pretraining. We benchmark eight state-of-the-art pruning algorithms in the context of TA-VLP, experimenting with two VLMs, three vision-language tasks, and three pruning ratios. Our experimental results show that MULTIFLOW outperforms recent sophisticated, combinatorial competitors in the vast majority of the cases, paving the way towards addressing TA- VLP. The code is publicly available at https://github.com/FarinaMatteo/multiflow.

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.

We study open-world multi-label text classification under extremely weak supervision (XWS), where the user only provides a brief description for classification objectives without any labels or ground-truth label space.Similar single-label XWS settings have been explored recently, however, these methods cannot be easily adapted for multi-label.We observe that (1) most documents have a dominant class covering the majority of content and (2) long-tail labels would appear in some documents as a dominant class.Therefore, we first utilize the user description to prompt a large language model (LLM) for dominant keyphrases of a subset of raw documents, and then construct a (initial) label space via clustering.We further apply a zero-shot multi-label classifier to locate the documents with small top predicted scores, so we can revisit their dominant keyphrases for more long-tail labels.We iterate this process to discover a comprehensive label space and construct a multi-label classifier as a novel method, X-MLClass.X-MLClass exhibits a remarkable increase in ground-truth label space coverage on various datasets, for example, a 40% improvement on the AAPD dataset over topic modeling and keyword extraction methods.Moreover, X-MLClass achieves the best end-to-end multi-label classification accuracy. B Prompt Templates for Generating KeyphrasesCode 2 provides an example of the prompt used to generate keyphrases for a selected chunk of the Amazon-531 dataset.Users can help us define the objective with examples.For example, the coarse-grained objectives look like "games" and "animals", while the corresponding fine-grained objectives are "trading_card_games" and "reptiles".

Many machine learning problems today have multiple objective functions, which are often tackled by the multi-objective learning (MOL) framework. Albeit many encouraging results are obtained by MOL algorithms, a recent theoretical study [1] revealed that these gradient-based MOL methods (e.g., MGDA, CAGrad) all reflect an inherent trade-off between optimization convergence speeds and conflict-avoidance abilities. To this end, we develop an improved stochastic variance-reduced multi-objective gradient correction method for MOL, achieving the ${\mathcal{O}}\left({{\varepsilon ^{ - 1.5}}}\right)$ sample complexity. In addition, our proposed method simultaneously improves the theoretical guarantees for conflict avoidance and convergence rate compared to prior stochastic gradient-based MOL methods in the non-convex setting. We further validate the effectiveness of the proposed method empirically using popular multi-task learning (MTL) benchmarks.

Gradient-based bilevel optimization methods have been applied to a wide range of applications including hyper-parameter optimization, meta-learning, and model pruning. However, it is known that the bilevel optimization problem is difficult to solve, and the finite-time guarantee has only been established for simpler bilevel problems with a strongly-convex lower-level problem. In this work, we propose an iterative bilevel optimization method that sequentially solves simple approximate problems of the original problem. Despite the lack of strong convexity in the lower level, we show that the proposed method converges to an ϵ-stationary-point with an iteration complexity of $\mathcal{O}\left( {{\varepsilon ^{ - 1}}} \right)$. Experiments have verified the effectiveness of the method.

Robust perception is a vital component for ensuring safe autonomous driving. Automotive radar (77 to 81 GHz) offering weather-resilient sensing provides a complementary capability to the vision-or LiDAR-based autonomous driving systems. Raw radio-frequency (RF) radar tensors contain rich spatiotemporal semantics besides 3D location information. Most previous methods take in 3D (Doppler-range-azimuth) RF radar tensors, allowing prediction of an object’s location, heading angle, and size in bird’s-eye-view (BEV). However, they lack the ability to simultaneously infer objects’ size, orientation, and identity in the 3D space. To overcome this limitation, we propose a joint architecture, called CenterRadarNet, designed to facilitate high-resolution representation learning from 4D (Doppler-range-azimuth-elevation) radar data for 3D object detection and re-identification (reID) tasks. Moreover, we build an online tracker utilizing the learned appearance embedding for re-ID. CenterRadarNet achieves the state-of-the-art result on the K-Radar 3D object detection benchmark. In addition, we present the first 3D object-tracking result on the K-Radar dataset. CenterRadarNet shows consistent, robust performance in diverse driving scenarios, emphasizing its wide applicability. Code is available at: https://github.com/Andy-Cheng/CenterRadarNet

In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird’s Eye View (BEV) to greatly enhance overall detection and tracking performance. Our approach, Camera-Radar Associated Fusion Tracking Booster (CRAFTBooster) represents a pioneering effort to enhance radar-camera fusion in the tracking stage, contributing to improved 3D MOT accuracy. The superior experimental results on K-Radaar dataset, which exhibit 5-6% on IDF1 tracking performance gain, validate the potential of effective sensor fusion in advancing autonomous driving.

As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of LLMs in terms of privacy, copyright, etc. A conventional LLM unlearning task typically involves two goals: (1) The target LLM should forget the knowledge in the specified forget documents; and (2) it should retain the other knowledge that the LLM possesses, for which we assume access to a small number of retain documents. To achieve both goals, a mainstream class of LLM unlearning methods introduces an optimization framework with a combination of two objectives – maximizing the prediction loss on the forget documents while minimizing that on the retain documents, which suffers from two challenges, degenerated output and catastrophic forgetting. In this paper, we propose a novel unlearning framework called Unlearning from Logit Difference (ULD), which introduces an assistant LLM that aims to achieve the opposite of the unlearning goals: remembering the forget documents and forgetting the retain knowledge. ULD then derives the unlearned LLM by computing the logit difference between the target and the assistant LLMs. We show that such reversed objectives would naturally resolve both aforementioned challenges while significantly improving the training efficiency. Extensive experiments demonstrate that our method efficiently achieves the intended forgetting while preserving the LLM’s overall capabilities, reducing training time by more than threefold. Notably, our method loses 0% of model utility on the ToFU benchmark, whereas baseline methods may sacrifice 17% of utility on average to achieve comparable forget quality.

While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements than conventional methods like 'BadNets' in image classification. This is because the art necessitates modifications to the diffusion training and sampling procedures. Unlike the prior work, we investigate whether BadNets-like data poisoning methods can directly degrade the generation by DMs. In other words, if only the training dataset is contaminated (without manipulating the diffusion process), how will this affect the performance of learned DMs? In this setting, we uncover bilateral data poisoning effects that not only serve an adversarial purpose (compromising the functionality of DMs) but also offer a defensive advantage (which can be leveraged for defense in classification tasks against poisoning attacks). We show that a BadNets-like data poisoning attack remains effective in DMs for producing incorrect images (misaligned with the intended text conditions). Meanwhile, poisoned DMs exhibit an increased ratio of triggers, a phenomenon we refer to as 'trigger amplification', among the generated images. This insight can be then used to enhance the detection of poisoned training data. In addition, even under a low poisoning ratio, studying the poisoning effects of DMs is also valuable for designing robust image classifiers against such attacks. Last but not least, we establish a meaningful linkage between data poisoning and the phenomenon of data replications by exploring DMs' inherent data memorization tendencies. Code is available at https://github.com/OPTML-Group/BiBadDiff.

The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose UnlearnCanvas, a comprehensive high-resolution stylized image dataset that facilitates the evaluation of the unlearning of artistic styles and associated objects. This dataset enables the establishment of a standardized, automated evaluation framework with 7 quantitative metrics assessing various aspects of the unlearning performance for DMs. Through extensive experiments, we benchmark 9 state-of-the-art MU methods for DMs, revealing novel insights into their strengths, weaknesses, and underlying mechanisms. Additionally, we explore challenging unlearning scenarios for DMs to evaluate worst-case performance against adversarial prompts, the unlearning of finer-scale concepts, and sequential unlearning. We hope that this study can pave the way for developing more effective, accurate, and robust DM unlearning methods, ensuring safer and more ethical applications of DMs in the future. The dataset, benchmark, and codes are publicly available at this link.

Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test examples can be easier to predict than others. This paper presents EENet, a novel early-exiting scheduling framework for multi-exit DNN models. Instead of having every sample go through all DNN layers during prediction, EENet learns an early exit scheduler, which can intelligently terminate the inference earlier for certain predictions, which the model has high confidence of early exit. As opposed to previous early-exiting solutions with heuristics-based methods, our EENet framework optimizes an early-exiting policy to maximize model accuracy while satisfying the given per-sample average inference budget. Extensive experiments are conducted on four computer vision datasets (CIFAR-10, CIFAR-100, ImageNet, Cityscapes) and two NLP datasets (SST-2, AgNews). The results demonstrate that the adaptive inference by EENet can outperform the representative existing early exit techniques. We also perform a detailed visualization analysis of the comparison results to interpret the benefits of EENet.

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.

In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process to remove the influence of specific examples from a given model. Although exact unlearning can be achieved through complete model retraining using the remaining dataset, the associated computational costs have driven the development of efficient, approximate unlearning techniques. Moving beyond data-centric MU approaches, our study introduces a novel model-based perspective: model sparsification via weight pruning, which is capable of reducing the gap between exact unlearning and approximate unlearning. We show in both theory and practice that model sparsity can boost the multi-criteria unlearning performance of an approximate unlearner, closing the approximation gap, while continuing to be efficient. This leads to a new MU paradigm, termed prune first, then unlearn, which infuses a sparse prior to the unlearning process. Building on this insight, we also develop a sparsity-aware unlearning method that utilizes sparsity regularization to enhance the training process of approximate unlearning. Extensive experiments show that our proposals consistently benefit MU in various unlearning scenarios. A notable highlight is the 77% unlearning efficacy gain of fine-tuning (one of the simplest approximate unlearning methods) when using our proposed sparsity-aware unlearning method. Furthermore, we showcase the practical impact of our proposed MU methods through two specific use cases: defending against backdoor attacks, and enhancing transfer learning through source class removal. These applications demonstrate the versatility and effectiveness of our approaches in addressing a variety of machine learning challenges beyond unlearning for data privacy. Codes are available at https://github.com/OPTML-Group/Unlearn-Sparse.

Graph neural networks (GNNs) have found extensive applications in learning from graph data. However, real-world graphs often possess diverse structures and comprise nodes and edges of varying types. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures through techniques like graph augmentations and large-scale pre-training on a wider array of graphs. Balancing this diversity while avoiding increased computational costs and the notorious trainability issues of GNNs is crucial. This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures, without incurring explosive computational overhead. The proposed Graph Mixture of Experts (GMoE) model empowers individual nodes in the graph to dynamically and adaptively select more general information aggregation experts. These experts are trained to capture distinct subgroups of graph structures and to incorporate information with varying hop sizes, where those with larger hop sizes specialize in gathering information over longer distances. The effectiveness of GMoE is validated through a series of experiments on a diverse set of tasks, including graph, node, and link prediction, using the OGB benchmark. Notably, it enhances ROC-AUC by $1.81\%$ in ogbg-molhiv and by $1.40\%$ in ogbg-molbbbp, when compared to the non-MoE baselines. Our code is publicly available at https://github.com/VITA-Group/Graph-Mixture-of-Experts.

Massive data is often considered essential for deep learning applications, but it also incurs significant computational and infrastructural costs. Therefore, dataset pruning (DP) has emerged as an effective way to improve data efficiency by identifying and removing redundant training samples without sacrificing performance. In this work, we aim to address the problem of DP for transfer learning, i.e., how to prune a source dataset for improved pretraining efficiency and lossless finetuning accuracy on downstream target tasks. To our best knowledge, the problem of DP for transfer learning remains open, as previous studies have primarily addressed DP and transfer learning as separate problems. By contrast, we establish a unified viewpoint to integrate DP with transfer learning and find that existing DP methods are not suitable for the transfer learning paradigm. We then propose two new DP methods, label mapping and feature mapping, for supervised and self-supervised pretraining settings respectively, by revisiting the DP problem through the lens of source-target domain mapping. Furthermore, we demonstrate the effectiveness of our approach on numerous transfer learning tasks. We show that source data classes can be pruned by up to $40\%\sim 80\%$ without sacrificing the downstream performance, resulting in a significant $2\sim 5\times$ speed-up during the pretraining stage. Besides, our proposal exhibits broad applicability and can improve other computationally intensive transfer learning techniques, such as adversarial pretraining.

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.

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.

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.

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.

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.

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.

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.

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.

Event detection from real surveillance videos with complicated background environment is always a very hard task. Different from the traditional retrospective and interactive systems designed on this task, which are mainly executed on video fragments located within the event-occurrence time, in this paper we propose a new interactive system constructed on the mid-level discriminative representations (patches/shots) which are closely related to the event (might occur beyond the event-occurrence period) and are easier to be detected than video fragments. By virtue of such easily-distinguished mid-level patterns, our framework realizes an effective labor division between computers and human participants. The task of computers is to train classifiers on a bunch of mid-level discriminative representations, and to sort all the possible mid-level representations in the evaluation sets based on the classifier scores. The task of human participants is then to readily search the events based on the clues offered by these sorted mid-level representations. For computers, such mid-level representations, with more concise and consistent patterns, can be more accurately detected than video fragments utilized in the conventional framework, and on the other hand, a human participant can always much more easily search the events of interest implicated by these location-anchored mid-level representations than conventional video fragments containing entire scenes. Both of these two properties facilitate the availability of our framework in real surveillance event detection applications.

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%.

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.

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.

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.