Optimization‐based text‑to‑3D methods distill guidance from 2D generative models via Score Distillation Sampling (SDS), but implicitly treat this guidance as static. This work shows that ignoring source dynamics yields inconsistent trajectories that suppress or merge semantic cues, leading to "semantic over-smoothing" artifacts. As such, we reformulate text‑to‑3D optimization as mapping a *dynamically evolving source* distribution to a fixed target distribution. We cast the problem into a dual‑conditioned latent space, conditioned on both the text prompt and the intermediately rendered image. Given this joint setup, we observe that the image condition naturally anchors the current source distribution. Building on this insight, we introduce AnchorDS, an improved score distillation mechanism that provides state‑anchored guidance with image conditions and stabilizes generation. We further penalize erroneous source estimates and design a lightweight filter strategy and fine‑tuning strategy that refines the anchor with negligible overhead. AnchorDS produces finer-grained detail, more natural colours, and stronger semantic consistency, particularly for complex prompts, while maintaining efficiency. Extensive experiments show that our method surpasses previous methods in both quality and efficiency.

Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decision-making and heavy reliance on scene-text recognition. In this paper, we propose to studyGrounded TextVideoQAby forcing models to answer questions and spatio-temporally localize the relevant scene-text regions, thus decoupling QA from scene-text recognition and promoting research towards interpretable QA. The task has three-fold significance. First, it encourages scene-text evidence versus other short-cuts for answer predictions. Second, it directly accepts scene-text regions as visual answers, thus circumventing the problem of ineffective answer evaluation by stringent string matching. Third, it isolates the challenges inherited in VideoQA and scene-text recognition. This enables the diagnosis of the root causes for failure predictions,e.g., wrong QA or wrong scene-text recognition? To achieve Grounded TextVideoQA, we propose the T2S-QA model that highlights a disentangled temporal-to-spatial contrastive learning strategy for weakly-supervised scene-text grounding and grounded TextVideoQA. To facilitate evaluation, we construct a new datasetViTXT-GQAwhich features 52Kscene-text bounding boxes within 2.2Ktemporal segments related to 2Kquestions and 729 videos. With ViTXT-GQA, we perform extensive experiments and demonstrate the severe limitations of existing techniques in Grounded TextVideoQA. While T2S-QA achieves superior results, the large performance gap with human leaves ample space for improvement. Our further analysis of oracle scene-text inputs posits that the major challenge is scene-text recognition. To advance the research of Grounded TextVideoQA, our dataset and code are athttps://github.com/zhousheng97/ViTXT-GQA.git

We present InstructHumans, a novel framework for instruction-driven animatable 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distillation Sampling (SDS). SDS, designed for generation tasks, cannot account for the defining requirement of editing – maintaining consistency with the source avatar. This work shows that naively using SDS harms editing, as it may destroy consistency. We propose a modified SDS for Editing (SDS-E) that selectively incorporates subterms of SDS across diffusion timesteps. We further enhance SDS-E with spatial smoothness regularization and gradient-based viewpoint sampling for edits with sharp and high-fidelity detailing. Incorporating SDS-E into a 3D human texture editing framework allows us to outperform existing 3D editing methods. Our avatars faithfully reflect the textual edits while remaining consistent with the original avatars. Project page: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://jyzhu.top/instruct-humans/</uri>.

Recent synthetic 3D human datasets for the face, body, and hands have pushed the limits on photorealism. Face recognition and body pose estimation have achieved state-of-the-art performance using synthetic training data alone, but for the hand, there is still a large synthetic-to-real gap. This paper presents the first systematic study of the synthetic-to-real gap of 3D hand pose estimation. We analyze the gap and identify key components such as the forearm, image frequency statistics, hand pose, and object occlusions. To facilitate our analysis, we propose a data synthesis pipeline to synthesize high-quality data. We demonstrate that synthetic hand data can achieve the same level of accuracy as real data when integrating our identified components, paving the path to use synthetic data alone for hand pose estimation. Code and data are available at: https://github.com/delaprada/HandSynthesis.git.

Standard 3D Gaussian Splatting (3DGS) relies on known or pre-computed camera poses and a sparse point cloud, obtained from structure-from-motion (SfM) preprocessing, to initialize and grow 3D Gaussians. We propose a novel SfM-Free 3DGS (HT-3DGS) method for video input, eliminating the need for known camera poses and SfM preprocessing. Our approach introduces a hierarchical training strategy that trains and merges multiple 3D Gaussian representations – each optimized for specific scene regions – into a single, unified 3DGS model representing the entire scene. To compensate for large camera motions, we leverage video frame interpolation models. Additionally, we incorporate multi-source supervision to reduce overfitting and enhance representation. Experimental results reveal that our approach significantly surpasses state-of-the-art SfM-free novel view synthesis methods. On the Tanks and Temples dataset, we improve PSNR by an average of 2.25dB, with a maximum gain of 3.72dB in the best scene. On the CO3D-V2 dataset, we achieve an average PSNR boost of 1.74dB, with a top gain of 3.90dB. The code is available at https://github.com/jibo27/3DGS_Hierarchical_Training.

This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to condense data into compact latent codes with significant storage reduced across temporal and channel aspects. Orthogonally, we propose sampling diverse and representative action sequences to minimize video-wise redundancy. Our evaluation on standard benchmarks demonstrates consistent effectiveness in condensing TAS datasets and achieving competitive performances. Specifically, on the Breakfast dataset, our approach reduces storage by over 500× while retaining 83% of the performance compared to training with the full dataset. Furthermore, when applied to a downstream incremental learning task, it yields superior performance compared to the state-of-the-art.

Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency –a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model’s responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations in video contents, language queries, and task settings, unveiling severe deficiencies in maintaining consistency. We further explore common prompting and instruction-tuning methods as potential solutions, but find that their improvements are often unstable. To that end, we propose event temporal verification tuning that explicitly accounts for consistency, and demonstrate significant improvements for both grounding and consistency. Our data and code are open-sourced at https://github.com/minjoong507/Consistency-of-Video-LLM.

Online Action Detection (OAD) detects actions in streaming videos using past observations. State-of-the-art OAD approaches model past observations and their interactions with an anticipated future. The past is encoded using short-and long-term memories to capture immediate and long-range dependencies, while anticipation compensates for missing future context. We identify a training-inference discrepancy in existing OAD methods that hinders learning effectiveness. The training uses varying lengths of short-term memory, while inference relies on a full-length short-term memory. As a remedy, we propose a Context-enhanced Memory-Refined Transformer (CMeRT). CMeRT introduces a context-enhanced encoder to improve frame representations using additional near-past context. It also features a memory-refined decoder to leverage near-future generation to enhance performance. CMeRT1achieves state-of-the-art in online detection and anticipation on THUMOS’14, CrossTask, and EPIC-Kitchens-100.

We introduce EgoTextVQA, a novel and rigorously constructed benchmark for egocentric QA assistance involving scene text. EgoTextVQA contains 1.5K ego-view videos and 7K scene-text aware questions that reflect real user needs in outdoor driving and indoor house-keeping activities. The questions are designed to elicit identification and reasoning on scene text in an egocentric and dynamic environment. With EgoTextVQA, we comprehensively evaluate 10 prominent multimodal large language models. Currently, all models struggle, and the best results (Gemini 1.5 Pro) are around 33% accuracy, highlighting the severe deficiency of these techniques in egocentric QA assistance. Our further investigations suggest that precise temporal grounding and multi-frame reasoning, along with high resolution and auxiliary scene-text inputs, are key for better performance. With thorough analyses and heuristic suggestions, we hope EgoTextVQA can serve as a solid testbed for research in egocentric scene-text QA assistance. Our dataset is released at: https://github.com/zhousheng97/EgoTextVQA.

3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM) algorithms; however, SfM is time-consuming and restricts the application of 3DGS in real-world scenarios and large-scale scene reconstruction. We introduce a constrained optimization method for simultaneous camera pose estimation and 3D reconstruction that does not require SfM support. Core to our approach is decomposing a camera pose into a sequence of camera-to-(device-)center and (device-)center-to-world optimizations. To facilitate, we propose two optimization constraints conditioned to the sensitivity of each parameter group and restricts each parameter's search space. In addition, as we learn the scene geometry directly from the noisy point clouds, we propose geometric constraints to improve the reconstruction quality. Experiments demonstrate that the proposed method significantly outperforms the existing (multi-modal) 3DGS baseline and methods supplemented by COLMAP on both our collected dataset and two public benchmarks.

Given a textual query along with a corresponding video, the objective of moment retrieval aims to localize the moments relevant to the query within the video. While commendable results have been demonstrated by existing transformer-based approaches, predicting the accurate temporal span of the target moment is still a major challenge. This paper reveals that a crucial reason stems from the spurious correlation between the text query and the moment context. Namely, the model makes predictions by overly associating queries with background frames rather than distinguishing target moments. To address this issue, we propose a dynamic learning approach for moment retrieval, where two strategies are designed to mitigate the spurious correlation. First, we introduce a novel video synthesis approach to construct a dynamic context for the queried moment, enabling the model to attend to the target moment of the corresponding query across dynamic backgrounds. Second, to alleviate the over-association with backgrounds, we enhance representations temporally by incorporating text-dynamics interaction, which encourages the model to align text with target moments through complementary dynamic representations. With the proposed method, our model significantly alleviates the spurious correlation issue in moment retrieval and establishes new state-of-the-art performance on two popular benchmarks, \ie, QVHighlights and Charades-STA. In addition, detailed ablation studies and evaluations across different architectures demonstrate the generalization and effectiveness of the proposed strategies. Our code will be publicly available.

Spurious correlations often arise when models associate features strongly correlated with, but not causally related to, the label e.g. an image classifier associates bodies of water with ducks. To mitigate spurious correlations, existing methods focus on learning unbiased representation or incorporating additional information about the correlations during training. This work removes spurious correlations by ``**E**rasing **wi**th **A**ctivations'' (EvA). EvA learns class-specific spurious indicator on each channel for the fully connected layer of pretrained networks. By erasing spurious connections during re-weighting, EvA achieves state-of-the-art performance across diverse datasets (6.2\% relative gain on BAR and achieves 4.1\% on Waterbirds). For biased datasets without any information about the spurious correlations, EvA can outperform previous methods (4.8\% relative gain on Waterbirds) with 6 orders of magnitude less compute, highlighting its data and computational efficiency.

For deep regression, preserving the ordinality of the targets with respect to the feature representation improves performance across various tasks. However, a theoretical explanation for the benefits of ordinality is still lacking. This work reveals that preserving ordinality reduces the conditional entropy $H(Z|Y)$ of representation $Z$ conditional on the target $Y$. However, our findings reveal that typical regression losses fail to sufficiently reduce $H(Z|Y)$, despite its crucial role in generalization performance. With this motivation, we introduce an optimal transport-based regularizer to preserve the similarity relationships of targets in the feature space to reduce $H(Z|Y)$. Additionally, we introduce a simple yet efficient strategy of duplicating the regressor targets, also with the aim of reducing $H(Z|Y)$. Experiments on three real-world regression tasks verify the effectiveness of our strategies to improve deep regression. Code: https://github.com/needylove/Regression_tightness

Vision Transformers (ViT) are remarkable at 3D pose estimation, yet they still encounter certain challenges. One issue is that the popular ViT architecture for pose estimation is limited to images and lacks temporal information. Another challenge is that the prediction often fails to maintain pixel alignment with the original images. To address these issues, we propose a systematic framework for 3D pose estimation, called ExtPose. ExtPose extends image ViT to the challenging scenario and video setting by taking in additional 2D pose evidence and capturing temporal information in a full attention-based manner. We use 2D human skeleton images to integrate structured 2D pose information. By sharing parameters and attending across modalities and frames, we enhance the consistency between 3D poses and 2D videos without introducing additional parameters. We achieve state-of-the-art (SOTA) performance on multiple human and hand pose estimation benchmarks with substantial improvements to 34.0mm (-23%) on 3DPW and 4.9mm (-18%) on FreiHAND in PA-MPJPE over the other ViT-based methods respectively.

This work highlights a semantics misalignment in 3D human pose estimation. For the task of test-time adaptation, the misalignment manifests as overly smoothed and unguided predictions. The smoothing settles predictions towards some average pose. Furthermore, when there are occlusions or truncations, the adaptation becomes fully unguided. To this end, we pioneer the integration of a semantics-aware motion prior for the test-time adaptation of 3D pose estimation. We leverage video understanding and a well-structured motion-text space to adapt the model motion prediction to adhere to video semantics during test time. Additionally, we incorporate a missing 2D pose completion based on the motion-text similarity. The pose completion strengthens the motion prior’s guidance for occlusions and truncations. Our method significantly improves state-of-the-art 3D human pose estimation TTA techniques, with more than 12% decrease in PA-MPJPE on 3DPW and 3DHP.

Video Question Answering (Video QA) has emerged as a central task in multimodal learning. This tutorial provides a comprehensive overview of VideoQA research and highlights new frontiers. We begin with an introduction to VideoQA preliminaries, tracing how methods have adapted from third-person view short videos to capture egocentric and long-ranged spatial-temporal dynamics. We then focus on the impact of large multimodal models. Next, we expand the scope to spatial understanding beyond videos. Each topic is discussed through the lens of tasks, datasets, methods, and evaluation protocols. Finally, we conclude with future directions, including fine-grained and long-ranged video understanding, robustness and trustworthiness, Egocentric and embodied assistance, and omnimodal integration. This tutorial aims to equip participants with both a historical perspective and a forward-looking roadmap for advancing Video QA in the LLM era.

We present EgoBlind, the first egocentric VideoQA dataset collected from blind individuals to evaluate the assistive capabilities of contemporary multimodal large language models (MLLMs). EgoBlind comprises 1,392 first-person videos from the daily lives of blind and visually impaired individuals. It also features 5,311 questions directly posed or verified by the blind to reflect their in-situation needs for visual assistance. Each question has an average of 3 manually annotated reference answers to reduce subjectiveness.Using EgoBlind, we comprehensively evaluate 16 advanced MLLMs and find that all models struggle. The best performers achieve an accuracy near 60\%, which is far behind human performance of 87.4\%. To guide future advancements, we identify and summarize major limitations of existing MLLMs in egocentric visual assistance for the blind and explore heuristic solutions for improvement. With these efforts, we hope that EgoBlind will serve as a foundation for developing effective AI assistants to enhance the independence of the blind and visually impaired. Data and code are available at \url{https://github.com/doc-doc/EgoBlind}.

State-of-the-art video deblurring methods use deep network architectures to recover sharpened video frames. Blurring especially degrades high-frequency (HF) information, yet this aspect is often overlooked by recent models that focus more on enhancing architectural design. Recovering these fine details is challenging, partly due to the spectral bias of neural networks, which are inclined towards learning low-frequency functions. To address this, we enforce explicit network structures to capture the fine details and edges. We dynamically predict adaptive high-pass kernels from a linear combination of high-pass basis kernels to extract high-frequency features. This strategy is highly efficient, resulting in low-memory footprints for training and fast run times for inference, all while achieving state-of-the-art when compared to low-budget models. The code is available at https://github.com/jibo27/AHFNet.

Assembly tasks, as an integral part of daily routines and activities, involve a series of sequential steps that are prone to error. This paper proposes a novel method for identifying ordering mistakes in assembly tasks based on knowledge-grounded beliefs. The beliefs comprise spatial and temporal aspects, each serving a unique role. Spatial beliefs capture the structural relationships among assembly components and indicate their topological feasibility. Temporal beliefs model the action preconditions and enforce sequencing constraints. Furthermore, we introduce a learning algorithm that dynamically updates and augments the belief sets online. To evaluate, we first test our approach in deducing predefined rules on synthetic data based on industry assembly. We also verify our approach on the real-world Assembly101 dataset, enhanced with annotations of component information. Our framework achieves superior performance in detecting ordering mistakes under both synthetic and real-world settings, highlighting the effectiveness of our approach. • We present two belief sets for the assembly tasks. • We propose a novel mistake detection framework for assembly tasks. • The framework can better detect ordering mistakes and can be integrated with perception modules.

Data replay is a successful incremental learning technique for images. It prevents catastrophic forgetting by keeping a reservoir of previous data, original or synthe-sized, to ensure the model retains past knowledge while adapting to novel concepts. However, its application in the video domain is rudimentary, as it simply stores frame ex-emplars for action recognition. This paper presents the first exploration of video data replay techniques for incremen-tal action segmentation, focusing on action temporal modeling. We propose a Temporally Coherent Action (TCA) model, which represents actions using a generative model instead of storing individual frames. The integration of a conditioning variable that captures temporal coherence al-lows our model to understand the evolution of action features over time. Therefore, action segments generated by TCA for replay are diverse and temporally coherent. In a 10-task incremental setup on the Breakfast dataset, our approach achieves significant increases in accuracy for up to 22% compared to the baselines.

Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification — a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are equipped for uncertainty estimation but cannot scale to large DNNs where they are highly unstable to train. To address this challenge, we introduce the Adaptable Bayesian Neural Network (ABNN), a simple and scalable strategy to seamlessly transform DNNs into BNNs in a post-hoc manner with minimal computational and training overheads. ABNN preserves the main predictive properties of DNNs while enhancing their uncertainty quantification abilities through simple BNN adaptation layers (attached to normalization layers) and a few fine-tuning steps on pretrained models. We conduct extensive experiments across multiple datasets for image classification and semantic segmentation tasks, and our results demonstrate that ABNN achieves state-of-the-art performance without the computational budget typically associated with ensemble methods.

We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously provide visual evidence, we seek to ascertain the extent to which the predictions of such techniques are genuinely anchored in relevant video content, versus spurious correlations from language or irrelevant visual context. Towards this, we construct NExT-GQA - an extension of NExT-QA with 10.5K temporal grounding (or location) labels tied to the original QA pairs. With NExT-GQA, we scrutinize a series of state-of-the-art VLMs. Through post-hoc attention analysis, we find that these models are extremely weak in substantiating the answers despite their strong QA performance. This exposes the limitation of current VLMs in making reliable predictions. As a remedy, we further explore and propose a grounded-QA method via Gaussian mask optimization and cross-modal learning. Experiments with different backbones demonstrate that this grounding mechanism improves both grounding and QA. With these efforts, we aim to push towards trustworthy VLMs in VQA systems. Our dataset and code are available at https://github.com/doc-doc/NExT-GQA.

Regression tasks in computer vision such as age estimation or counting are often formulated into classification by quantizing the target space into classes. Yet real-world data is often imbalanced - the majority of training samples lie in a head range of target values while a minority of samples span a usually larger tail range. By selecting the class quantization one can adjust imbalanced re-gression targets into balanced classification outputs though there are trade-offs in balancing classification accuracy and quantization error. To improve regression performance over the entire range of data we propose to construct hierarchical classifiers for solving imbalanced regression tasks. The fine-grained classifiers limit the quantization error while being modulated by the coarse predictions to ensure high accuracy. Standard hierarchical classification approaches when applied to the regression problem fail to ensure that predicted ranges remain consistent across the hierarchy. As such we propose a range-preserving distillation process that effectively learns a single classifier from the set of hierarchical classifiers. Our novel hierarchical classification adjustment (HCA) for imbalanced regression shows superior results on three diverse tasks age estimation crowd counting and depth estimation. Code is available at https: / / gi thub. com/xhp-hust −2018-2011/HCA

In video super-resolution, it is common to use a frame-wise alignment to support the propagation of information over time. The role of alignment is well-studied for low-level enhancement in video, but existing works overlook a critical step - resampling. We show through extensive experiments that for alignment to be effective, the resam-pIing should preserve the reference frequency spectrum while minimizing spatial distortions. However, most ex-isting works simply use a default choice of bilinear inter-polation for resampling even though bilinear interpolation has a smoothing effect and hinders super-resolution. From these observations, we propose an implicit resampling-based alignment. The sampling positions are encoded by a sinusoidal positional encoding, while the value is es-timated with a coordinate network and a window-based cross-attention. We show that bilinear interpolation inher-ently attenuates high-frequency information while an MLP-based coordinate network can approximate more frequen-cies. Experiments on synthetic and real-world datasets show that alignment with our proposed implicit resampling enhances the performance of state-of-the-art frameworks with minimal impact on both compute and parameters.

2D keypoints are commonly used as an additional cue to refine estimated 3D human meshes. Current methods opti-mize the pose and shape parameters with a reprojection loss on the provided 2D keypoints. Such an approach, while sim-ple and intuitive, has limited effectiveness because the opti-mal solution is hard to find in ambiguous parameter space and may sacrifice depth. Additionally, divergent gradients from distal joints complicate and deviate the refinement of proximal joints in the kinematic chain. To address these, we introduce Kinematic-Tree Rotation (KITRO), a novel mesh refinement strategy that explicitly models depth and human kinematic-tree structure. KITRO treats refinement from a bone-wise perspective. Unlike previous methods which per-form gradient-based optimizations, our method calculates bone directions in closed form. By accounting for the 2D pose, bone length, and parent joint's depth, the calculation results in two possible directions for each child joint. We then use a decision tree to trace binary choices for all bones along the human skeleton's kinematic-tree to select the most probable hypothesis. Our experiments across var-ious datasets and baseline models demonstrate that KITRO significantly improves 3D joint estimation accuracy and achieves an ideal 2D fit simultaneously. Our code available at: https://github.com/MartaYang/KITRO.

Activation shaping has proven highly effective for identifying out-of-distribution (OOD) samples post-hoc. Activation shaping prunes and scales network activations before estimating the OOD energy score; such an extremely simple approach achieves state-of-the-art OOD detection with minimal in-distribution (ID) accuracy drops. This paper analyzes the working mechanism behind activation shaping. We directly show that the benefits for OOD detection derive only from scaling, while pruning is detrimental. Based on our analysis, we propose SCALE, an even simpler yet more effective post-hoc network enhancement method for OOD detection. SCALE attains state-of-the-art OOD detection performance without any compromises on ID accuracy. Furthermore, we integrate scaling concepts into learning and propose Intermediate Tensor SHaping (ISH) for training-time OOD detection enhancement. ISH achieves significant AUROC improvements for both near- and far-OOD, highlighting the importance of activation distributions in emphasizing ID data characteristics. Our code and models are available at https://github.com/kai422/SCALE.

2D human pose estimation predicts keypoint locations and the corresponding confidence. Calibration-wise, the confidence should be aligned with the pose accuracy. Yet existing pose estimation methods tend to estimate confidence with heuristics such as the maximum value of heatmaps. This work shows, through theoretical analysis and empirical verification, a calibration gap in current pose estimation frameworks. Our derivations directly lead to closed-form adjustments in the confidence based on additionally inferred instance size and visibility. Given the black-box nature of deep neural networks, however, it is not possible to close the gap with only closed-form adjustments. We go one step further and propose a Calibrated ConfidenceNet (CCNet) to explicitly learn network-specific adjustments with a confidence prediction branch. The proposed CCNet, as a lightweight post-hoc addition, improves the calibration of standard off-the-shelf pose estimation frameworks.

Most works studying representation learning focus only on classification and neglect regression. Yet, the learning objectives and, therefore, the representation topologies of the two tasks are fundamentally different: classification targets class separation, leading to disconnected representations, whereas regression requires ordinality with respect to the target, leading to continuous representations. We thus wonder how the effectiveness of a regression representation is influenced by its topology, with evaluation based on the Information Bottleneck (IB) principle. The IB principle is an important framework that provides principles for learning effective representations. We establish two connections between it and the topology of regression representations. The first connection reveals that a lower intrinsic dimension of the feature space implies a reduced complexity of the representation $Z$. This complexity can be quantified as the conditional entropy of $Z$ on the target $Y$, and serves as an upper bound on the generalization error. The second connection suggests a feature space that is topologically similar to the target space will better align with the IB principle. Based on these two connections, we introduce PH-Reg, a regularizer specific to regression that matches the intrinsic dimension and topology of the feature space with the target space. Experiments on synthetic and real-world regression tasks demonstrate the benefits of PH-Reg. Code: https://github.com/needylove/PH-Reg.

Conditional diffusion models can create unseen images in various settings, aiding image interpolation. Interpolation in latent spaces is well-studied, but interpolation with specific conditions like text or image is less understood. Common approaches interpolate linearly in the conditioning space but tend to result in inconsistent images with poor fidelity. This work introduces a novel training-free technique named \textbf{Attention Interpolation via Diffusion (AID)}. AID has two key contributions: \textbf{1)} a fused inner/outer interpolated attention layer to boost image consistency and fidelity; and \textbf{2)} selection of interpolation coefficients via a beta distribution to increase smoothness. Additionally, we present an AID variant called \textbf{Prompt-guided Attention Interpolation via Diffusion (PAID)}, which \textbf{3)} treats interpolation as a condition-dependent generative process. Experiments demonstrate that our method achieves greater consistency, smoothness, and efficiency in condition-based interpolation, aligning closely with human preferences. Furthermore, PAID offers substantial benefits for compositional generation, controlled image editing, image morphing and image-controlled generation, all while remaining training-free.

Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context information in an online setting remains an under-explored problem. This work presents the first online framework for temporal action segmentation. At the core of the framework is an adaptive memory designed to accommodate dynamic changes in context over time, alongside a feature augmentation module that enhances the frames with the memory. In addition, we propose a post-processing approach to mitigate the severe over-segmentation in the online setting. On three common segmentation benchmarks, our approach achieves state-of-the-art performance.

Semantic segmentation methods have advanced significantly. Still, their robustness to real-world perturbations and object types not seen during training remains a challenge, particularly in safety-critical applications. We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models. Specifically, we design Robusta, a novel robust conditional generative adversarial network to generate realistic and plausible perturbed images that can be used to train reliable segmentation models. We conduct in-depth studies of the proposed generative model, assess the performance and robustness of the downstream segmentation network, and demonstrate that our approach can significantly enhance the robustness in the face of real-world perturbations, distribution shifts, and out-of-distribution samples. Our results suggest that this approach could be valuable in safety-critical applications, where the reliability of perception modules such as semantic segmentation is of utmost importance and comes with a limited computational budget in inference. We release our code at github.com/ENSTA-U2IS/robusta.

Occlusion is a common challenge in human pose estimation. Curiously, learning from occluded keypoints hinders a model to detect visible keypoints. We speculate that the impairment is likely due to a forced correlation between keypoints and visual features of the occluders. As such, we propose a novel visibility-aware attention mechanism to eliminate unreliable occluding features. The explicit occlusion handling encourages the model to reason about occluded keypoints using evidence and contextual information from the visible keypoints. It also mitigates the damage of unreliable correlations of the occluded keypoints. Our method, when added to the strong baseline SimCC, improves by 1.3 AP and 0.7 AP with ResNet and HRNet respectively. It also surpasses the state-of-the-art I2R-Net on CrowdPose by 0.3 AP and 0.6 APhard. The improvements highlight that rethinking visibility information is critical for developing effective human pose estimation systems.

Temporal action segmentation (TAS) in videos aims at densely identifying video frames in minutes-long videos with multiple action classes. As a long-range video understanding task, researchers have developed an extended collection of methods and examined their performance using various benchmarks. Despite the rapid growth of TAS techniques in recent years, no systematic survey has been conducted in these sectors. This survey analyzes and summarizes the most significant contributions and trends. In particular, we first examine the task definition, common benchmarks, types of supervision, and prevalent evaluation measures. In addition, we systematically investigate two essential techniques of this topic, i.e., frame representation and temporal modeling, which have been studied extensively in the literature. We then conduct a thorough review of existing TAS works categorized by their levels of supervision and conclude our survey by identifying and emphasizing several research gaps.

We present Pose Integrated Gradient (PoseIG), the first interpretability technique designed for pose estimation. We extend the concept of integrated gradients for pose estimation to generate pixel-level attribution maps. To enable comparison across different pose frameworks, we unify different pose outputs into a common output space, along with a likelihood approximation function for gradient back-propagation. To complement the qualitative insight from the attribution maps, we propose three indices for quantitative analysis. With these tools, we systematically compare different pose estimation frameworks to understand the impacts of network design, backbone and auxiliary tasks. Our analysis reveals an interesting shortcut of the knuckles (MCP joints) for hand pose estimation and an under-explored inversion error for keypoints in body pose estimation. Project page and code: https://qy-h00.github.io/poseig/.

Recent advances in hand pose estimation have shed light on utilizing synthetic data to train neural networks, which however inevitably hinders generalization to real-world data due to domain gaps. To solve this problem, we present a framework for cross-domain semi-supervised hand pose estimation and target the challenging scenario of learning models from labelled multimodal synthetic data and unlabelled real-world data. To that end, we propose a dual-modality network that exploits synthetic RGB and synthetic depth images. For pre-training, our network uses multi-modal contrastive learning and attention-fused supervision to learn effective representations of the RGB images. We then integrate a novel self-distillation technique during fine-tuning to reduce pseudo-label noise. Experiments show that the proposed method significantly improves 3D hand pose estimation and 2D keypoint detection on benchmarks.

Direct mesh fitting for 3D hand shape reconstruction is highly accurate. However, the reconstructed meshes are prone to artifacts and do not appear as plausible hand shapes. Conversely, parametric models like MANO ensure plausible hand shapes but are not as accurate as the non-parametric methods. In this work, we introduce a novel weakly-supervised hand shape estimation framework that integrates non-parametric mesh fitting with MANO model in an end-to-end fashion. Our joint model overcomes the tradeoff in accuracy and plausibility to yield well-aligned and high-quality 3D meshes, especially in challenging two-hand and hand-object interaction scenarios.

For monocular RGB-based 3D pose and shape estimation, multiple solutions are often feasible due to factors like occlusions and truncations. This work presents a multi-hypothesis probabilistic framework by optimizing the Kullback–Leibler divergence (KLD) between the data and model distribution. Our formulation reveals a connection between the pose entropy and diversity in the multiple hypotheses that has been neglected by previous works. For a comprehensive evaluation, besides the best hypothesis (BH) metric, we factor in visibility for evaluating diversity. Additionally, our framework is label-friendly – it can be learned from only partial 2D keypoints, such as visible keypoints. Experiments on both ambiguous and real-world benchmarks demonstrate that our method outperforms other state-of-the-art multi-hypothesis methods. The project page is at https://gloryyrolg.github.io/MHEntropy.

Human actions in egocentric videos often feature hand-object interactions composed of a verb (performed by the hand) applied to an object. Despite their extensive scaling up, egocentric datasets still face two limitations — sparsity of action compositions and a closed set of interacting objects. This paper proposes a novel open vocabulary action recognition task. Given a set of verbs and objects observed during training, the goal is to generalize the verbs to an open vocabulary of actions with seen and novel objects. To this end, we decouple the verb and object predictions via an object-agnostic _verb encoder_ and a prompt-based _object encoder_. The prompting leverages CLIP representations to predict an open vocabulary of interacting objects. We create open vocabulary benchmarks on the EPIC-KITCHENS-100 and Assembly101 datasets; whereas closed-action methods fail to generalize, our proposed method is effective. In addition, our object encoder significantly outperforms existing open-vocabulary visual recognition methods in recognizing novel interacting objects.

Pose estimation is remarkably successful under supervised learning, but obtaining annotations, especially for new deployments, is costly and time-consuming. This work tackles adapting models trained on synthetic data to real-world target domains with only unlabelled data. A common approach is model fine-tuning with pseudo-labels from the target domain; yet many pseudo-labelling strategies cannot provide sufficient high-quality pose labels. This work proposes a reconstruction-based strategy as a complement to pseudo-labelling for synthetic-to-real domain adaptation. We generate the driving image by geometrically transforming a base image according to the predicted keypoints and enforce a reconstruction loss to refine the predictions. It provides a novel solution to effectively correct confident yet inaccurate keypoint locations through image reconstruction in domain adaptation. Our approach outperforms the previous state-of-the-arts by 8% for PCK on four large-scale hand and human real-world datasets. In particular, we excel on endpoints such as fingertips and head, with 7.2% and 29.9% improvements in PCK.

In human and hand pose estimation, heatmaps are a crucial intermediate representation for a body or hand keypoint. Two popular methods to decode the heatmap into a final joint coordinate are via an argmax, as done in heatmap detection, or via softmax and expectation, as done in integral regression. Integral regression is learnable end-to-end, but has lower accuracy than detection. This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation. This bias often forces the network to learn degenerately localized heatmaps, obscuring the keypoint's true underlying distribution and leads to lower accuracies. Training-wise, by investigating the gradients of integral regression, we show that the implicit guidance of integral regression to update the heatmap makes it slower to converge than detection. To counter the above two limitations, we propose Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias. BCIR also incorporates a Gaussian prior loss to speed up training and improve prediction accuracy. Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.

Can we teach a robot to recognize and make predictions for activities that it has never seen before? We tackle this problem by learning models for video from text. This paper presents a hierarchical model that generalizes instructional knowledge from large-scale text corpora and transfers the knowledge to video. Given a portion of an instructional video, our model recognizes and predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the capabilities of our model, we introduce the Tasty Videos Dataset V2, a collection of 4022 recipes for zero-shot learning, recognition and anticipation. Extensive experiments with various evaluation metrics demonstrate the potential of our method for generalization, given limited video data for training models.

Temporal action segmentation tags action labels for every frame in an input untrimmed video containing multiple actions in a sequence. For the task of temporal action segmentation, we propose an encoder-decoder style architecture named C2F-TCN featuring a "coarse-to-fine" ensemble of decoder outputs. The C2F-TCN framework is enhanced with a novel model agnostic temporal feature augmentation strategy formed by the computationally inexpensive strategy of the stochastic max-pooling of segments. It produces more accurate and well-calibrated supervised results on three benchmark action segmentation datasets. We show that the architecture is flexible for both supervised and representation learning. In line with this, we present a novel unsupervised way to learn frame-wise representation from C2F-TCN. Our unsupervised learning approach hinges on the clustering capabilities of the input features and the formation of multi-resolution features from the decoder's implicit structure. Further, we provide first semi-supervised temporal action segmentation results by merging representation learning with conventional supervised learning. Our semi-supervised learning scheme, called "Iterative-Contrastive-Classify (ICC)", progressively improves in performance with more labeled data. The ICC semi-supervised learning in C2F-TCN, with 40% labeled videos, performs similar to fully supervised counterparts.

We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional cross-modal interaction modules. 3) It is optimized by the joint fully- and self-supervised contrastive objectives between the correct and incorrect answers, as well as the relevant and irrelevant questions respectively. With superior video encoding and QA solution, we show that CoVGT can achieve much better performances than previous arts on video reasoning tasks. Its performances even surpass those models that are pretrained with millions of external data. We further show that CoVGT can also benefit from cross-modal pretraining, yet with orders of magnitude smaller data. The results demonstrate the effectiveness and superiority of CoVGT, and additionally reveal its potential for more data-efficient pretraining.

The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to collect. This work is the first to propose a Constituent Action Discovery (CAD) framework that only requires the video-wise high-level complex activity label as supervision for temporal action segmentation. The proposed approach automatically discovers constituent video actions using an activity classification task. Specifically, we define a finite number of latent action prototypes to construct video-level dual representations with which these prototypes are learned collectively through the activity classification training. This setting endows our approach with the capability to discover potentially shared actions across multiple complex activities. Due to the lack of action-level supervision, we adopt the Hungarian matching algorithm to relate latent action prototypes to ground truth semantic classes for evaluation. We show that with the high-level supervision, the Hungarian matching can be extended from the existing video and activity levels to the global level. The global-level matching allows for action sharing across activities, which has never been considered in the literature before. Extensive experiments demonstrate that our discovered actions can help perform temporal action segmentation and activity recognition tasks.

Video anomaly detection aims to automatically identify unusual objects or behaviours by learning from normal videos. Previous methods tend to use simplistic reconstruction or prediction constraints, which leads to the insufficiency of learned representations for normal data. As such, we propose a novel bi-directional architecture with three consistency constraints to comprehensively regularize the prediction task from pixel-wise, cross-modal, and temporal-sequence levels. First, predictive consistency is proposed to consider the symmetry property of motion and appearance in forwards and backwards time, which ensures the highly realistic appearance and motion predictions at the pixel-wise level. Second, association consistency considers the relevance between different modalities and uses one modality to regularize the prediction of another one. Finally, temporal consistency utilizes the relationship of the video sequence and ensures that the predictive network generates temporally consistent frames. During inference, the pattern of abnormal frames is unpredictable and will therefore cause higher prediction errors. Experiments show that our method outperforms advanced anomaly detectors and achieves state-of-the-art results on UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets.

Temporal action segmentation classifies the action of each frame in (long) video sequences. Due to the high cost of frame-wise labeling, we propose the first semi-supervised method for temporal action segmentation. Our method hinges on unsupervised representation learning, which, for temporal action segmentation, poses unique challenges. Actions in untrimmed videos vary in length and have unknown labels and start/end times. Ordering of actions across videos may also vary. We propose a novel way to learn frame-wise representations from temporal convolutional networks (TCNs) by clustering input features with added time-proximity conditions and multi-resolution similarity. By merging representation learning with conventional supervised learning, we develop an "Iterative Contrast-Classify (ICC)'' semi-supervised learning scheme. With more labelled data, ICC progressively improves in performance; ICC semi-supervised learning, with 40% labelled videos, performs similarly to fully-supervised counterparts. Our ICC improves MoF by {+1.8, +5.6, +2.5}% on Breakfast, 50Salads, and GTEA respectively for 100% labelled videos.

Video question answering requires the models to understand and reason about both the complex video and language data to correctly derive the answers. Existing efforts have been focused on designing sophisticated cross-modal interactions to fuse the information from two modalities, while encoding the video and question holistically as frame and word sequences. Despite their success, these methods are essentially revolving around the sequential nature of video- and question-contents, providing little insight to the problem of question-answering and lacking interpretability as well. In this work, we argue that while video is presented in frame sequence, the visual elements (e.g., objects, actions, activities and events) are not sequential but rather hierarchical in semantic space. To align with the multi-granular essence of linguistic concepts in language queries, we propose to model video as a conditional graph hierarchy which weaves together visual facts of different granularity in a level-wise manner, with the guidance of corresponding textual cues. Despite the simplicity, our extensive experiments demonstrate the superiority of such conditional hierarchical graph architecture, with clear performance improvements over prior methods and also better generalization across different type of questions. Further analyses also demonstrate the model's reliability as it shows meaningful visual-textual evidences for the predicted answers.

Video deblurring has achieved remarkable progress thanks to the success of deep neural networks. Most methods solve for the deblurring end-to-end with limited information propagation from the video sequence. However, different frame regions exhibit different characteristics and should be provided with corresponding relevant information. To achieve fine-grained deblurring, we designed a memory branch to memorize the blurry-sharp feature pairs in the memory bank, thus providing useful information for the blurry query input. To enrich the memory of our memory bank, we further designed a bidirectional recurrency and multi-scale strategy based on the memory bank. Experimental results demonstrate that our model outperforms other state-of-the-art methods while keeping the model complexity and inference time low. The code is available at https://github.com/jibo27/MemDeblur.

Assembly101 is a new procedural activity dataset fea-turing 4321 videos of people assembling and disassembling 101 “take-apart” toy vehicles. Participants work without fixed instructions, and the sequences feature rich and natu-ral variations in action ordering, mistakes, and corrections. Assembly101 is the first multi-view action dataset, with si-multaneous static (8) and egocentric (4) recordings. Se-quences are annotated with more than 100K coarse and 1M fine-grained action segments, and I8M 3D hand poses. We benchmark on three action understanding tasks: recognition, anticipation and temporal segmentation. Ad-ditionally, we propose a novel task of detecting mistakes. The unique recording format and rich set of annotations al-low us to investigate generalization to new toys, cross-view transfer, long-tailed distributions, and pose vs. appearance. We envision that Assemblyl0l will serve as a new challenge to investigate various activity understanding problems.

We propose a novel approach to generate temporally coherent UV coordinates for loose clothing. Our method is not constrained by human body outlines and can capture loose garments and hair. We implemented a differentiable pipeline to learn UV mapping between a sequence of RGB inputs and textures via UV coordinates. Instead of treating the UV coordinates of each frame separately, our data generation approach connects all UV coordinates via feature matching for temporal stability. Subsequently, a generative model is trained to balance the spatial quality and temporal stability. It is driven by supervised and unsupervised losses in both UV and image spaces. Our experiments show that the trained models output high-quality UV coordinates and generalize to new poses. Once a sequence of UV co-ordinates has been inferred by our model, it can be used to flexibly synthesize new looks and modified visual styles. Compared to existing methods, our approach reduces the computational workload to animate new outfits by several orders of magnitude.

We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from keyframes to other frames in a bidirectional and multi-hop manner. Additionally, we introduce a residual-based correction module that can fix wrongly propagated segmentation masks from noisy or erroneous motion vectors. Our approach is flexible and can be added on top of several existing video object segmentation algorithms. We achieved highly competitive results on DAVIS17 and YouTube-VOS on various base models with substantial speed-ups of up to 3.5X with minor drops in accuracy.11Code: https://github.com/kai422/CoVOS

We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks targeting causal action reasoning, temporal action reasoning, and common scene comprehension. Through extensive analysis of baselines and established VideoQA techniques, we find that top-performing methods excel at shallow scene descriptions but are weak in causal and temporal action reasoning. Furthermore, the models that are effective on multi-choice QA, when adapted to open-ended QA, still struggle in generalizing the answers. This raises doubt on the ability of these models to reason and highlights possibilities for improvement. With detailed results for different question types and heuristic observations for future works, we hope NExT-QA will guide the next generation of VQA research to go beyond superficial description towards a deeper understanding of videos. (The dataset and related resources are available at https://github.com/doc-doc/NExT-QA.git).

Heatmap-based detection methods are dominant for 2D human pose estimation even though regression is more intuitive. The introduction of the integral regression method, which, architecture-wise uses an implicit heatmap, brings the two approaches even closer together. This begs the question – does detection really outperform regression? In this paper, we investigate the difference in supervision between the heatmap-based detection and integral regression, as this is the key remaining difference between the two approaches. In the process, we discover an underlying bias behind integral pose regression that arises from taking the expectation after the softmax function. To counter the bias, we present a compensation method which we find to improve integral regression accuracy on all 2D pose estimation benchmarks. We further propose a simple combined detection and bias-compensated regression method that considerably outperforms state-of-the-art baselines with few added components.

We present SemiHand, a semi-supervised framework for 3D hand pose estimation from monocular images. We pre-train the model on labelled synthetic data and fine-tune it on unlabelled real-world data by pseudo-labeling with consistency training. By design, we introduce data augmentation of differing difficulties, consistency regularizer, label correction and sample selection for RGB-based 3D hand pose estimation. In particular, by approximating the hand masks from hand poses, we propose a cross-modal consistency and leverage semantic predictions to guide the predicted poses. Meanwhile, we introduce pose registration as label correction to guarantee the biomechanical feasibility of hand bone lengths. Experiments show that our method achieves a favorable improvement on real-world datasets after fine-tuning.

Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead significantly restricts their practical deployments on resource-limited devices. In this paper, we proposed a novel contrastive self-distillation (CSD) framework to simultaneously compress and accelerate various off-the-shelf SR models. In particular, a channel-splitting super-resolution network can first be constructed from a target teacher network as a compact student network. Then, we propose a novel contrastive loss to improve the quality of SR images and PSNR/SSIM via explicit knowledge transfer. Extensive experiments demonstrate that the proposed CSD scheme effectively compresses and accelerates several standard SR models such as EDSR, RCAN and CARN. Code is available at https://github.com/Booooooooooo/CSD.

In interactive instance segmentation, users give feedback to iteratively refine segmentation masks. The user-provided clicks are transformed into guidance maps which provide the network with necessary cues on the whereabouts of the object of interest. Guidance maps used in current systems are purely distance-based and are either too localized or non-informative. We propose a novel transformation of user clicks to generate content-aware guidance maps that leverage the hierarchical structural information present in an image. Using our guidance maps, even the most basic FCNs are able to outperform existing approaches that require state-of-the-art segmentation networks pre-trained on large scale segmentation datasets. We demonstrate the effectiveness of our proposed transformation strategy through comprehensive experimentation in which we significantly raise state-of-the-art on four standard interactive segmentation benchmarks.

We present a self-supervision method for 3D hand pose estimation from depth maps. We begin with a neural network initialized with synthesized data and fine-tune it on real but unlabelled depth maps by minimizing a set of data-fitting terms. By approximating the hand surface with a set of spheres, we design a differentiable hand renderer to align estimates by comparing the rendered and input depth maps. In addition, we place a set of priors including a data-driven term to further regulate the estimate's kinematic feasibility. Our method makes highly accurate estimates comparable to current supervised methods which require large amounts of labelled training samples, thereby advancing state-of-the-art in unsupervised learning for hand pose estimation.

Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint. To better analyze these factors of variation, we propose the use of disentangled representations and a disentangled variational autoencoder (dVAE) that allows for specific sampling and inference of these factors. The derived objective from the variational lower bound as well as the proposed training strategy are highly flexible, allowing us to handle cross-modal encoders and decoders as well as semi-supervised learning scenarios. Experiments show that our dVAE can synthesize highly realistic images of the hand specifiable by both pose and image background content and also estimate 3D hand poses from RGB images with accuracy competitive with state-of-the-art on two public benchmarks.

How can we teach a robot to predict what will happen next for an activity it has never seen before? We address the problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual domain. Given a portion of an instructional video, our model predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the anticipation capabilities of our model, we introduce the Tasty Videos dataset, a collection of 2511 recipes for zero-shot learning, recognition and anticipation.

Hand pose estimation from monocular RGB inputs is a highly challenging task. Many previous works for monocular settings only used RGB information for training despite the availability of corresponding data in other modalities such as depth maps. In this work, we propose to learn a joint latent representation that leverages other modalities as weak labels to boost the RGB-based hand pose estimator. By design, our architecture is highly flexible in embedding various diverse modalities such as heat maps, depth maps and point clouds. In particular, we find that encoding and decoding the point cloud of the hand surface can improve the quality of the joint latent representation. Experiments show that with the aid of other modalities during training, our proposed method boosts the accuracy of RGB-based hand pose estimation systems and significantly outperforms state-of-the-art on two public benchmarks.

This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input. We propose an iterative discriminative-generative approach which alternates between discriminatively learning the appearance of sub-activities from the videos' visual features to sub-activity labels and generatively modelling the temporal structure of sub-activities using a Generalized Mallows Model. In addition, we introduce a model for background to account for frames unrelated to the actual activities. Our approach is validated on the challenging Breakfast Actions and Inria Instructional Videos datasets and outperforms both unsupervised and weakly-supervised state of the art.

We present a simple and effective method for 3D hand pose estimation from a single depth frame. As opposed to previous state-of-the-art methods based on holistic 3D regression, our method works on dense pixel-wise estimation. This is achieved by careful design choices in pose parameterization, which leverages both 2D and 3D properties of depth map. Specifically, we decompose the pose parameters into a set of per-pixel estimations, i.e., 2D heat maps, 3D heat maps and unit 3D directional vector fields. The 2D/3D joint heat maps and 3D joint offsets are estimated via multitask network cascades, which is trained end-to-end. The pixel-wise estimations can be directly translated into a vote casting scheme. A variant of mean shift is then used to aggregate local votes while enforcing consensus between the the estimated 3D pose and the pixel-wise 2D and 3D estimations by design. Our method is efficient and highly accurate. On MSRA and NYU hand dataset, our method outperforms all previous state-of-the-art approaches by a large margin. On the ICVL hand dataset, our method achieves similar accuracy compared to the nearly saturated result obtained by [5] and outperforms various other proposed methods. Code is available online1.

Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from complex representations. We present a novel complex gated recurrent cell, which is a hybrid cell combining complex-valued and norm-preserving state transitions with a gating mechanism. The resulting RNN exhibits excellent stability and convergence properties and performs competitively on the synthetic memory and adding task, as well as on the real-world tasks of human motion prediction.

State-of-the-art methods for 3D hand pose estimation from depth images require large amounts of annotated training data. We propose modelling the statistical relationship of 3D hand poses and corresponding depth images using two deep generative models with a shared latent space. By design, our architecture allows for learning from unlabeled image data in a semi-supervised manner. Assuming a one-to-one mapping between a pose and a depth map, any given point in the shared latent space can be projected into both a hand pose or into a corresponding depth map. Regressing the hand pose can then be done by learning a discriminator to estimate the posterior of the latent pose given some depth map. To prevent over-fitting and to better exploit unlabeled depth maps, the generator and discriminator are trained jointly. At each iteration, the generator is updated with the back-propagated gradient from the discriminator to synthesize realistic depth maps of the articulated hand, while the discriminator benefits from an augmented training set of synthesized samples and unlabeled depth maps. The proposed discriminator network architecture is highly efficient and runs at 90fps on the CPU with accuracies comparable or better than state-of-art on 3 publicly available benchmarks.

Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and detailed depth map. We also define a novel set loss over multiple images; by regularizing the estimation between a common set of images, the network is less prone to overfitting and achieves better accuracy than competing methods. Experiments on the NYU Depth v2 dataset shows that our depth predictions are competitive with state-of-the-art and lead to faithful 3D projections.

We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence. We use neighborhood graphs for the partitioning and the similarity information in the graph is further exploited to cluster the motion primitives into larger entities of semantic significance. The method requires no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. In addition, we introduce a feature bundling preprocessing technique to make the segmentation more robust to noise, as well as a notion of motion symmetry for more refined primitive detection. We test our method on several sensor modalities, including markered and markerless motion capture as well as on electromyograph and accelerometer recordings. The results highlight our system's capabilities for both segmentation and for analysis of the finer structures of motion data, all in a completely unsupervised manner.

A novel superpixel extraction algorithm using a higher order energy optimization framework is proposed in this paper. We first adopt the k-means clustering technique to quickly get an initial superpixel result. Then a higher order energy function is employed to optimize and refine these initial superpixels. We use a more general higher order energy function that includes a first-order data term, a second-order smoothness term, and a higher order term. The presegments are employed to provide the prior information of sufficient edges and segment regions for our higher order energy term. According to the texture measurement in different local regions, our algorithm adaptively computes the proper ratios of different energy terms to obtain a better superpixel performance. The experimental results demonstrate that our method using the higher order energy generates better results with well-aligned boundaries and homogeneous effects than the existing superpixel algorithms.

Human gestures, similar to speech and handwriting, are often unique to the individual. Training a generic classifier applicable to everyone can be very difficult and as such, it has become a standard to use personalized classifiers in speech and handwriting recognition. In this paper, we address the problem of personalization in the context of gesture recognition, and propose a novel and extremely efficient way of doing personalization. Unlike conventional personalization methods which learn a single classifier that later gets adapted, our approach learns a set (portfolio) of classifiers during training, one of which is selected for each test subject based on the personalization data. We formulate classifier personalization as a selection problem and propose several algorithms to compute the set of candidate classifiers. Our experiments show that such an approach is much more efficient than adapting the classifier parameters but can still achieve comparable or better results.

In recent years, the rise of digital image and video data available has led to an increasing demand for image annotation. In this paper, we propose an interactive object annotation method that incrementally trains an object detector while the user provides annotations. In the design of the system, we have focused on minimizing human annotation time rather than pure algorithm learning performance. To this end, we optimize the detector based on a realistic annotation cost model based on a user study. Since our system gives live feedback to the user by detecting objects on the fly and predicts the potential annotation costs of unseen images, data can be efficiently annotated by a single user without excessive waiting time. In contrast to popular tracking-based methods for video annotation, our method is suitable for both still images and video. We have evaluated our interactive annotation approach on three datasets, ranging from surveillance, television, to cell microscopy.

Early works on human action recognition focused on tracking and classifying articulated body motions. Such methods required accurate localisation of body parts, which is a difficult task, particularly under realistic imaging conditions. As such, recent trends have shifted towards the use of more abstract, low-level appearance features such as spatio-temporal interest points. Motivated by the recent progress in pose estimation, we feel that pose-based action recognition systems warrant a second look. In this paper, we address the question of whether pose estimation is useful for action recognition or if it is better to train a classifier only on low-level appearance features drawn from video data. We compare pose-based, appearance-based and combined pose and appearance features for action recognition in a home-monitoring scenario. Our experiments show that pose-based features outperform low-level appearance features, even when heavily corrupted by noise, suggesting that pose estimation is beneficial for the action recognition task. © 2011. The copyright of this document resides with its authors.

A common approach for handling the complexity and inherent ambiguities of 3D human pose estimation is to use pose priors learned from training data. Existing approaches however, are either too simplistic (linear), too complex to learn, or can only learn latent spaces from "simple data", i.e., single activities such as walking or running. In this paper, we present an efficient stochastic gradient descent algorithm that is able to learn probabilistic non-linear latent spaces composed of multiple activities. Furthermore, we derive an incremental algorithm for the online setting which can update the latent space without extensive relearning. We demonstrate the effectiveness of our approach on the task of monocular and multi-view tracking and show that our approach outperforms the state-of-the-art.

Abstract—The paper introduces Hough forests, which are random forests adapted to perform a generalized Hough transform in an efficient way. Compared to previous Hough-based systems such as implicit shape models, Hough forests improve the performance of the generalized Hough transform for object detection on a categorical level. At the same time, their flexibility permits extensions of the Hough transform to new domains such as object tracking and action recognition. Hough forests can be regarded as task-adapted codebooks of local appearance that allow fast supervised training and fast matching at test time. They achieve high detection accuracy since the entries of such codebooks are optimized to cast Hough votes with small variance and since their efficiency permits dense sampling of local image patches or video cuboids during detection. The efficacy of Hough forests for a set of computer vision tasks is validated through experiments on a large set of publicly available benchmark data sets and comparisons with the state-of-the-art.

We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled feature patches and their corresponding votes in a spatio-temporal-action Hough space. The leaves of the trees form a discriminative multi-class codebook that share features between the action classes and vote for action centers in a probabilistic manner. Using low-level features such as gradients and optical flow, we demonstrate that Hough-voting can achieve state-of-the-art performance on several datasets covering a wide range of action-recognition scenarios.