Related papers: H$_{2}$OT: Hierarchical Hourglass Tokenizer for Ef…

Feature fusion plays a pivotal role in achieving high performance in vision models, yet existing attention-based fusion techniques often suffer from substantial computational overhead and implementation complexity, particularly in…

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation,…

This paper proposes a unified framework dubbed Multi-view and Temporal Fusing Transformer (MTF-Transformer) to adaptively handle varying view numbers and video length without camera calibration in 3D Human Pose Estimation (HPE). It consists…

In this paper we present a novel method to estimate 3D human pose and shape from monocular videos. This task requires directly recovering pixel-alignment 3D human pose and body shape from monocular images or videos, which is challenging due…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require…

Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…

In this research, we address the challenge faced by existing deep learning-based human mesh reconstruction methods in balancing accuracy and computational efficiency. These methods typically prioritize accuracy, resulting in large network…

Human pose estimation (HPE) is one of the most challenging tasks in computer vision as humans are deformable by nature and thus their pose has so much variance. HPE aims to correctly identify the main joint locations of a single person or…

In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented language generation. While many recent transformer models…

Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning offers significant savings, but existing approaches…

Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper…

There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. However, existing transformer-based methods treat body joints as…

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore…

Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with…

Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune…

Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are…

In the current state of 6D pose estimation, top-performing techniques depend on complex intermediate correspondences, specialized architectures, and non-end-to-end algorithms. In contrast, our research reframes the problem as a…

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit…