Related papers: Multi-Stage Spatio-Temporal Aggregation Transforme…

We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual…

Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity…

This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and free-viewpoint talking portrait synthesis, given an identity embedding or reference image,…

Leveraging Transformer attention has led to great advancements in HDR deghosting. However, the intricate nature of self-attention introduces practical challenges, as existing state-of-the-art methods often demand high-end GPUs or exhibit…

Human pose estimation in low-resolution videos presents a fundamental challenge in computer vision. Conventional methods either assume high-quality inputs or employ computationally expensive cascaded processing, which limits their…

Human Activity Recognition is an important task in many human-computer collaborative scenarios, whilst having various practical applications. Although uni-modal approaches have been extensively studied, they suffer from data quality and…

Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…

We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the…

The current paper proposes a novel neural network model for recognizing visually perceived human actions. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by introducing multiple timescale…

Although significant achievements have been achieved by recurrent neural network (RNN) based video prediction methods, their performance in datasets with high resolutions is still far from satisfactory because of the information loss…

Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific…

Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. To this end, we…

Face Presentation Attack Detection (PAD) is an important measure to prevent spoof attacks for face biometric systems. Many works based on Convolution Neural Networks (CNNs) for face PAD formulate the problem as an image-level binary…

Accurate 3D human pose estimation is a challenging task due to occlusion and depth ambiguity. In this paper, we introduce a multi-hop graph transformer network designed for 2D-to-3D human pose estimation in videos by leveraging the…

Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…

Micro-expression recognition (MER) is a challenging task due to the subtle and fleeting nature of micro-expressions. Traditional input modalities, such as Apex Frame, Optical Flow, and Dynamic Image, often fail to adequately capture these…

Understanding actions within surgical workflows is critical for evaluating post-operative outcomes and enhancing surgical training and efficiency. Capturing and analyzing long sequences of actions in surgical settings is challenging due to…

Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. However, the self-attention module highly relies on the…

This paper strives to solve complex video question answering (VideoQA) which features long video containing multiple objects and events at different time. To tackle the challenge, we highlight the importance of identifying question-critical…

Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE) typically adopt a two-stage strategy, which first detects human instances in each frame and then performs single-person PSE with temporal model. However, the…