Related papers: Training-Free Zero-Shot Temporal Action Detection …
Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common…
Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further…
Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security…
Autism Spectrum Disorder (ASD) presents significant challenges in early diagnosis and intervention, impacting children and their families. With prevalence rates rising, there is a critical need for accessible and efficient screening tools.…
Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications. Previous methods rely on tedious annotations of temporal action boundaries for training, which…
Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making…
This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…
Temporal Action Detection (TAD), the task of localizing and classifying actions in untrimmed video, remains challenging due to action overlaps and variable action durations. Recent findings suggest that TAD performance is dependent on the…
Temporal action detection is a fundamental yet challenging task in video understanding. Many of the state-of-the-art methods predict the boundaries of action instances based on predetermined anchors akin to the two-dimensional object…
Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging pretrained vision-language models (VLMs) to localize target…
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…
Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot recognition by comparing image embeddings to text-derived class prototypes. However, under domain shift, they suffer from feature drift, class-prior mismatch, and severe…
Current action recognition methods heavily rely on trimmed videos for model training. However, it is expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture,…
Existing temporal action localization (TAL) works rely on a large number of training videos with exhaustive segment-level annotation, preventing them from scaling to new classes. As a solution to this problem, few-shot TAL (FS-TAL) aims to…
Video Anomaly Detection~(VAD) focuses on identifying anomalies within videos. Supervised methods require an amount of in-domain training data and often struggle to generalize to unseen anomalies. In contrast, training-free methods leverage…
Understanding human behavior and activity facilitates advancement of numerous real-world applications, and is critical for video analysis. Despite the progress of action recognition algorithms in trimmed videos, the majority of real-world…
The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning,…
Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…
Spatio-temporal action detection encompasses the tasks of localizing and classifying individual actions within a video. Recent works aim to enhance this process by incorporating interaction modeling, which captures the relationship between…
Temporal Action Detection (TAD) requires precise localization of action boundaries within long, untrimmed video sequences. While current high-performing methods achieve strong accuracy, they are often characterized by excessive parameter…