Related papers: ActionHub: A Large-scale Action Video Description …

Temporal action localization (TAL) is an important and challenging problem in video understanding. However, most existing TAL benchmarks are built upon the coarse granularity of action classes, which exhibits two major limitations in this…

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form…

Zero-shot action recognition, which addresses the issue of scalability and generalization in action recognition and allows the models to adapt to new and unseen actions dynamically, is an important research topic in computer vision…

The performance of video action recognition has been significantly boosted by using motion representations within a two-stream Convolutional Neural Network (CNN) architecture. However, there are a few challenging problems in action…

Vision-language models (VLMs) classify the query video by calculating a similarity score between the visual features and text-based class label representations. Recently, large language models (LLMs) have been used to enrich the text-based…

Zero-Shot Anomaly Detection (ZSAD) seeks to identify anomalies from arbitrary novel categories, offering a scalable and annotation-efficient solution. Traditionally, most ZSAD works have been based on the CLIP model, which performs anomaly…

Event cameras have recently shown promising capabilities in instantaneous motion estimation due to their robustness to low light and fast motions. However, computing wide-baseline correspondence between two arbitrary views remains a…

Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remains challenging for current Video Foundation Models (VFMs). This difficulty stems from noisy web supervision and a…

Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involve objects. Existing…

Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard benchmarks, we are…

Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level representations for each video by designing inter-frame temporal modeling strategies or…

Despite the rapid progress, existing works on action understanding focus strictly on one type of action agent, which we call actor---a human adult, ignoring the diversity of actions performed by other actors. To overcome this narrow…

Zero-shot learning (ZSL) is a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges remain. Recently, methods using generative models to combat bias towards classes…

Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, we propose a novel approach that first summarizes each video into compound prototypes consisting of a…

In this paper, we introduce a new hierarchical model for human action recognition using body joint locations. Our model can categorize complex actions in videos, and perform spatio-temporal annotations of the atomic actions that compose the…

Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding. Unfortunately, due to a lack of sufficiently diverse…

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…

Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…

Human Activity Recognition (HAR) is a fundamental technology for numerous human - centered intelligent applications. Although deep learning methods have been utilized to accelerate feature extraction, issues such as multimodal data mixing,…

Despite being (pre)trained on a massive amount of data, state-of-the-art video-language alignment models are not robust to semantically-plausible contrastive changes in the video captions. Our work addresses this by identifying a broad…