Numerous well-annotated human key-point datasets are publicly available to date. However, annotating human poses for newly collected images is still a costly and time-consuming progress. Pose distributions from different datasets share similar pose hinge-structure priors with different geometric transformations, such as pivot orientation, joint rotation, and bone length ratio. The difference between Pose distributions is essentially the difference between the transformation distributions. Inspired by this fact, we propose a method to calibrate a pre-trained pose generator in which the pose prior has already been learned to an adapted one following a new pose distribution. We treat the representation of human pose joint coordinates as skeleton image and transfer a pre-trained pose annotation generator with only a few annotation guidance. By fine-tuning a limited number of linear layers that closely related to the pose transformation, the adapted generator is able to produce any number of pose annotations that are similar to the target poses. We evaluate our proposed method, FlexPose, on several cross-dataset settings both qualitatively and quantitatively, which demonstrates that our approach achieves state-of-the-art performance compared to the existing generative-model-based transfer learning methods when given limited annotation guidance.

Video moment retrieval aims to locate specific moments from a video according to the query text. This task presents two main challenges: i) aligning the query and video frames at the feature level, and ii) projecting the query-aligned frame features to the start and end boundaries of the matching interval. Previous work commonly involves all frames in feature alignment, easy to cause aligning irrelevant frames with the query. Furthermore, they forcibly map visual features to interval boundaries but ignoring the information gap between them, yielding suboptimal performance. In this study, to reduce distraction from irrelevant frames, we designate an anchor frame as that with the maximum query-frame relevance measured by the established Vision-Language Model. Via similarity comparison between the anchor frame and the others, we produce a semantically compact segment around the anchor frame, which serves as a guide to align features of query and related frames. We observe that such a feature alignment will make similarity cohesive between target frames, which enables us to predict the interval boundaries by a single point detection in the 2D semantic similarity space of frames, thus well bridging the information gap between frame semantics and temporal boundaries. Experimental results across various datasets demonstrate that our approach significantly improves the alignment between queries and video frames while effectively predicting temporal moment boundaries. Especially, on QVHighlights Test and ActivityNet Captions datasets, our proposed approach achieves 3.8% and 7.4% respectively higher than current state-of-the-art [email protected] performance. The code is available at https://github.com/ExMorgan-Alter/AFAFSGD.

Motion mapping between characters with different structures but corresponding to homeomorphic graphs, meanwhile preserving motion semantics and perceiving shape geometries, poses significant challenges in skinned motion retargeting. We propose M-R2ET, a modular neural motion retargeting system to comprehensively address these challenges. The key insight driving M-R2ET is its capacity to learn residual motion modifications within a canonical skeleton space. Specifically, a cross-structure alignment module is designed to learn joint correspondences among diverse skeletons, enabling motion copy and forming a reliable initial motion for semantics and geometry perception. Besides, two residual modification modules, i.e., the skeleton-aware module and shape-aware module, preserving source motion semantics and perceiving target character geometries, effectively reduce interpenetration and contact-missing. Driven by our distance-based losses that explicitly model the semantics and geometry, these two modules learn residual motion modifications to the initial motion in a single inference without post-processing. To balance these two motion modifications, we further present a balancing gate to conduct linear interpolation between them. Extensive experiments on the public dataset Mixamo demonstrate that our M-R2ET achieves the state-of-the-art performance, enabling cross-structure motion retargeting, and providing a good balance among the preservation of motion semantics as well as the attenuation of interpenetration and contact-missing

Learning with noisy label is a classic problem that has been extensively studied for image tasks, but much less for video in the literature. A straightforward migration from images to videos without considering temporal semantics and computational cost is not a sound choice. In this paper, we propose two new strategies for video analysis with noisy labels: 1) a lightweight channel selection method dubbed as Channel Truncation for feature-based label noise detection. This method selects the most discriminative channels to split clean and noisy instances in each category. 2) A novel contrastive strategy dubbed as Noise Contrastive Learning, which constructs the relationship between clean and noisy instances to regularize model training. Experiments on three well-known benchmark datasets for video classification show that our proposed truNcatE-split-contrAsT (NEAT) significantly outperforms the existing baselines. By reducing the dimension to 10% of it, our method achieves over 0.4 noise detection F1-score and 5% classification accuracy improvement on Mini-Kinetics dataset under severe noise (symmetric-80%). Thanks to Noise Contrastive Learning, the average classification accuracy improvement on Mini-Kinetics and Sth-Sth-V1 is over 1.6%.

A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware module is introduced to preserve the source motion semantics. A shape-aware module is designed to perceive the geometries of target characters to reduce interpenetration and contact-missing. Driven by our explored distance-based losses that explicitly model the motion semantics and geometry, these two modules can learn residual motion modifications on the source motion to generate plausible retargeted motion in a single inference without postprocessing. To balance these two modifications, we further present a balancing gate to conduct linear interpolation between them. Extensive experiments on the public dataset Mixamo demonstrate that our R2ET achieves the state-of-the-art performance, and provides a good balance between the preservation of motion semantics as well as the attenuation of interpenetration and contact-missing. Code is available at https://github.com/Kebii/R2ET.

This paper proposes an anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence. It deforms a garment mesh template by a mixture of rigid transformations with extra nonlinear displacements. A set of anchors around the mesh surface is introduced to guide the learning of rigid transformation matrices. Once the anchor transformations are found, per-vertex nonlinear displacements of the garment template can be regressed in a canonical space, which reduces the complexity of deformation space learning. By explicitly constraining the transformed anchors to satisfy the consistencies of position, normal and direction, the physical meaning of learned anchor transformations in space is guaranteed for better generalization. Furthermore, an adaptive anchor updating is proposed to optimize the anchor position by being aware of local mesh topology for learning representative anchor transformations. Qualitative and quantitative experiments on different types of garments demonstrate that AnchorDEF achieves the state-of-the-art performance on 3D garment deformation prediction in motion, especially for loose-fitting garments.

Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pretrained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first randomly select temporal regions, each of which contains multiple clips, from one video as pseudo actions and then paste them onto different temporal positions of the other two videos. The pretext task is to align the features of pasted pseudo action regions from two synthetic videos and maximize the agreement between them. Compared to the existing unsupervised video representation learning approaches, our PAL adapts better to downstream TAL tasks by introducing a temporal equivariant contrastive learning paradigm in a temporally dense and scale-aware manner. Extensive experiments show that PAL can utilize large-scale unlabeled video data to significantly boost the performance of existing TAL methods. Our codes and models will be made publicly available at https://github.com/zhang-can/UP-TAL.

The goal of early action recognition is to predict action label when the sequence is partially observed. The existing methods treat the early action recognition task as sequential classification problems on different observation ratios of an action sequence. Since these models are trained by differentiating positive category from all negative classes, the diverse information of different negative categories is ignored, which we believe can be collected to help improve the recognition performance. In this paper, we step towards to a new direction by introducing category exclusion to early action recognition. We model the exclusion as a mask operation on the classification probability output of a pre-trained early action recognition classifier. Specifically, we use policy-based reinforcement learning to train an agent. The agent generates a series of binary masks to exclude interfering negative categories during action execution and hence help improve the recognition accuracy. The proposed method is evaluated on three benchmark recognition datasets, NTU-RGBD, First-Person Hand Action, as well as UCF-101. The proposed method enhances the recognition accuracy consistently over all different observation ratios on the three datasets, where the accuracy improvements on the early stages are especially significant.

Despite the recent success of 3D action recognition using depth sensor, most existing works target how to improve the action recognition performance, rather than understanding how different types of actions are performed. In this paper, we propose to discover discriminative spatio-temporal patterns for 3D action recognition. Discovering these patterns can not only help to improve the action recognition performance but also help us to understand and differentiate between the action category. Our proposed method takes the spatio-temporal structure of 3D action into consideration and can discover essential spatio-temporal patterns that play key roles in action recognition. Instead of relying on an end-to-end network to learn the 3D action representation and perform classification, we simply present each 3D action as a series of temporal stages composed by 3D poses. Then, we rely on nearest neighbor matching and bilinear classifiers to simultaneously identify both critical temporal stages and spatial joints for each action class. Despite using raw action representation and a linear classifier, experiments on five benchmark data sets show that the proposed spatio-temporal naïve Bayes mutual information maximization can achieve a competitive performance compared with the state-of-the-art methods that use sophisticated end-to-end learning, and has the advantage of finding discriminative spatio-temporal action patterns.

Convolutional Neural Network (CNN) has shown promising results for 3D hand pose estimation in depth images. Different from existing CNN-based hand pose estimation methods that take either 2D images or 3D volumes as the input, our proposed Hand PointNet directly processes the 3D point cloud that models the visible surface of the hand for pose regression. Taking the normalized point cloud as the input, our proposed hand pose regression network is able to capture complex hand structures and accurately regress a low dimensional representation of the 3D hand pose. In order to further improve the accuracy of fingertips, we design a fingertip refinement network that directly takes the neighboring points of the estimated fingertip location as input to refine the fingertip location. Experiments on three challenging hand pose datasets show that our proposed method outperforms state-of-the-art methods.

Motivated by previous success of using non-parametric methods to recognize objects, e.g., NBNN [2], we extend it to recognize actions using skeletons. Each 3D action is presented by a sequence of 3D poses. Similar to NBNN, our proposed Spatio-Temporal-NBNN applies stage-to-class distance to classify actions. However, ST-NBNN takes the spatio-temporal structure of 3D actions into consideration and relaxes the Naive Bayes assumption of NBNN. Specifically, ST-NBNN adopts bilinear classifiers [19] to identify both key temporal stages as well as spatial joints for action classification. Although only using a linear classifier, experiments on three benchmark datasets show that by combining the strength of both non-parametric and parametric models, ST-NBNN can achieve competitive performance compared with state-of-the-art results using sophisticated models such as deep learning. Moreover, by identifying key skeleton joints and temporal stages for each action class, our ST-NBNN can capture the essential spatio-temporal patterns that play key roles of recognizing actions, which is not always achievable by using end-to-end models.