Related papers: RefAtomNet++: Advancing Referring Atomic Video Act…
Current strong pedestrian attribute recognition models are developed based on Transformer networks, which are computationally heavy. Recently proposed models with linear complexity (e.g., Mamba) have garnered significant attention and have…
Video-based person recognition is challenging due to persons being blocked and blurred, and the variation of shooting angle. Previous research always focused on person recognition on still images, ignoring similarity and continuity between…
Image-to-video generation has made remarkable progress with the advancements in diffusion models, yet generating videos with realistic motion remains highly challenging. This difficulty arises from the complexity of accurately modeling…
Adapting large Video-Language Models (VLMs) for action detection using only a few examples poses challenges like overfitting and the granularity mismatch between scene-level pre-training and required person-centric understanding. We propose…
Vision Language Place Recognition (VLVPR) enhances robot localization performance by incorporating natural language descriptions from images. By utilizing language information, VLVPR directs robot place matching, overcoming the constraint…
Recent few-shot action recognition (FSAR) methods typically perform semantic matching on learned discriminative features to achieve promising performance. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level,…
Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…
The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to…
With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large vision language models (LVLMs) have enhanced…
This paper presents a framework to recognize temporal compositions of atomic actions in videos. Specifically, we propose to express temporal compositions of actions as semantic regular expressions and derive an inference framework using…
In real-world action recognition systems, incorporating more attributes helps achieve a more comprehensive understanding of human behavior. However, using a single model to simultaneously recognize multiple attributes can lead to a decrease…
Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the…
Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition…
Recently, the soft attention mechanism, which was originally proposed in language processing, has been applied in computer vision tasks like image captioning. This paper presents improvements to the soft attention model by combining a…
Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) methods rely on linear interaction histories, which struggle to…
A fundamental requirement for real-world robotic deployment is the ability to understand and respond to natural language instructions. Existing language-conditioned manipulation tasks typically assume that instructions are perfectly aligned…
Handwritten Paragraph Text Recognition (HPTR) is a challenging task in Computer Vision, requiring the transformation of a paragraph text image, rich in handwritten text, into text encoding sequences. One of the most advanced models for this…
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome…
Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted…
Fitness movement recognition, a focused subdomain of human activity recognition (HAR), plays a vital role in health monitoring, rehabilitation, and personalized fitness training by enabling automated exercise classification from video data.…