Related papers: Zeus: Efficiently Localizing Actions in Videos usi…
Dense action detection involves detecting multiple co-occurring actions while action classes are often ambiguous and represent overlapping concepts. We argue that handling the dual challenge of temporal and class overlaps is too complex to…
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…
Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly learn image-based embedding space by leveraging powerful…
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…
Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the…
Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…
Accurate video annotation plays a vital role in modern retail applications, including customer behavior analysis, product interaction detection, and in-store activity recognition. However, conventional annotation methods heavily rely on…
We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to…
Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions. For example, videos of humans or…
Human action recognition is an important application domain in computer vision. Its primary aim is to accurately describe human actions and their interactions from a previously unseen data sequence acquired by sensors. The ability to…
Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos…
In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and…
Detecting actions in videos, particularly within cluttered scenes, poses significant challenges due to the limitations of 2D frame analysis from a camera perspective. Unlike human vision, which benefits from 3D understanding, recognizing…
Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. When humans watch videos, we can adapt our abstract-level knowledge about actions…
Automatic surgical gesture recognition is fundamental for improving intelligence in robot-assisted surgery, such as conducting complicated tasks of surgery surveillance and skill evaluation. However, current methods treat each frame…
Gaze is an essential prompt for analyzing human behavior and attention. Recently, there has been an increasing interest in determining gaze direction from facial videos. However, video gaze estimation faces significant challenges, such as…
Reinforcement Learning (RL) agents have demonstrated their potential across various robotic tasks. However, they still heavily rely on human-engineered reward functions, requiring extensive trial-and-error and access to target behavior…
Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time. To capture this intuition, we…
Video activity recognition has become increasingly important in robots and embodied AI. Recognizing continuous video activities poses considerable challenges due to the fast expansion of streaming video, which contains multi-scale and…
Despite the recent progress in video understanding and the continuous rate of improvement in temporal action localization throughout the years, it is still unclear how far (or close?) we are to solving the problem. To this end, we introduce…