Related papers: Post-Processing Temporal Action Detection
Large scale datasets created from crowdsourced labels or openly available data have become crucial to provide training data for large scale learning algorithms. While these datasets are easier to acquire, the data are frequently noisy and…
As a critical task in video sequence classification within computer vision, Online Action Detection (OAD) has garnered significant attention. The sensitivity of mainstream OAD models to varying video viewpoints often hampers their…
Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions,…
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…
Typical techniques for sequence classification are designed for well-segmented sequences which have been edited to remove noisy or irrelevant parts. Therefore, such methods cannot be easily applied on noisy sequences expected in real-world…
Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected…
Human action recognition (HAR) in videos is a fundamental research topic in computer vision. It consists mainly in understanding actions performed by humans based on a sequence of visual observations. In recent years, HAR have witnessed…
This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if…
Gait anomaly detection is a task that involves detecting deviations from a person's normal gait pattern. These deviations can indicate health issues and medical conditions in the healthcare domain, or fraudulent impersonation and…
Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it…
State-of-the-art temporal action detectors inefficiently search the entire video for specific actions. Despite the encouraging progress these methods achieve, it is crucial to design automated approaches that only explore parts of the video…
Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of…
In text-audio retrieval (TAR) tasks, due to the heterogeneity of contents between text and audio, the semantic information contained in the text is only similar to certain frames within the audio. Yet, existing works aggregate the entire…
Face presentation attack detection (PAD) plays an important role in defending face recognition systems against presentation attacks. The success of PAD largely relies on supervised learning that requires a huge number of labeled data, which…
Recently, temporal action localization (TAL), i.e., finding specific action segments in untrimmed videos, has attracted increasing attentions of the computer vision community. State-of-the-art solutions for TAL involves evaluating the…
Weakly-supervised temporal action localization (WTAL) aims to recognize and localize action instances with only video-level labels. Despite the significant progress, existing methods suffer from severe performance degradation when…
Without deploying face anti-spoofing countermeasures, face recognition systems can be spoofed by presenting a printed photo, a video, or a silicon mask of a genuine user. Thus, face presentation attack detection (PAD) plays a vital role in…
Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…
While Transformers have revolutionized machine learning on various data, existing Transformers for temporal graphs face limitations in (1) restricted receptive fields, (2) overhead of subgraph extraction, and (3) suboptimal generalization…
Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future. Current approaches typically treat TAA as a supervised learning task needing the laborious annotation of accident…