Related papers: BID: Boundary-Interior Decoding for Unsupervised T…

Spatio-temporal action detection (STAD) aims to classify the actions present in a video and localize them in space and time. It has become a particularly active area of research in computer vision because of its explosively emerging…

Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional…

3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and…

Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings…

This work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples. Where existing work relies on transferring global attribute or object information from seen to…

Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data. However, even the 3D skeletons captured in practice are still…

In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature…

We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos. Unlike conventional methods encoding motion and appearance patterns individually, our method puts particular…

Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks to extract framewise, whole-body-level motion…

Current self-supervised approaches for skeleton action representation learning often focus on constrained scenarios, where videos and skeleton data are recorded in laboratory settings. When dealing with estimated skeleton data in real-world…

Gait-based person re-identification (Re-ID) is valuable for safety-critical applications, and using only 3D skeleton data to extract discriminative gait features for person Re-ID is an emerging open topic. Existing methods either adopt…

As mobile robots increasingly operate in environments shared with humans, proactively anticipating human motion rather than responding reactively is critical for preempting collisions during close-proximity navigation, while maintaining…

Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to…

In the realm of autonomous driving, conventional approaches for vehicle perception and decision-making primarily rely on sensor input and rule-based algorithms. However, these methodologies often suffer from lack of interpretability and…

Current state-of-the-art methods for skeleton-based action recognition are supervised and rely on labels. The reliance is limiting the performance due to the challenges involved in annotation and mislabeled data. Unsupervised methods have…

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

In the near future, more and more machines will perform tasks in the vicinity of human spaces or support them directly in their spatially bound activities. In order to simplify the verbal communication and the interaction between robotic…

Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action boundaries by…

This paper introduces a probabilistic graphical model for continuous action recognition with two novel components: substructure transition model and discriminative boundary model. The first component encodes the sparse and global temporal…