相关论文: SFMViT: SlowFast Meet ViT in Chaotic World

Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory…

Simultaneous localization and mapping (SLAM) in slowly varying scenes is important for long-term robot task completion. Failing to detect scene changes may lead to inaccurate maps and, ultimately, lost robots. Classical SLAM algorithms…

Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive masking have been developed to reduce their sizes and…

Semi-supervised video object segmentation (VOS) aims to segment a few moving objects in a video sequence, where these objects are specified by annotation of first frame. The optical flow has been considered in many existing semi-supervised…

Accurate traffic flow prediction heavily relies on the spatio-temporal correlation of traffic flow data. Most current studies separately capture correlations in spatial and temporal dimensions, making it difficult to capture complex…

Predicting future motion trajectories is a critical capability across domains such as robotics, autonomous systems, and human activity forecasting, enabling safer and more intelligent decision-making. This paper proposes a novel, efficient,…

In this paper, we propose the use of a semantic image, an improved representation for video analysis, principally in combination with Inception networks. The semantic image is obtained by applying localized sparse segmentation using global…

Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels. Among these approaches, multimodal violence detection, which integrates modalities such as…

Video anomaly detection (VAD) aims to identify unexpected events in videos and has wide applications in safety-critical domains. While semi-supervised methods trained on only normal samples have gained traction, they often suffer from high…

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor…

Video fusion is a fundamental technique in various video processing tasks. However, existing video fusion methods heavily rely on optical flow estimation and feature warping, resulting in severe computational overhead and limited…

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which…

Centralized trajectory optimization in the joint space of multiple robots allows access to a larger feasible space that can result in smoother trajectories, especially while planning in tight spaces. Unfortunately, it is often…

Anomaly recognition plays a vital role in surveillance, transportation, healthcare, and public safety. However, most existing approaches rely solely on visual data, making them unreliable under challenging conditions such as occlusion, low…

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks. Although early exiting is a feasible solution for…

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

For the deployment of neural networks in resource-constrained environments, prior works have built lightweight architectures with convolution and attention for capturing local and global dependencies, respectively. Recently, the state space…

This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets. To achieve an accurate and computationally efficient tracker, this paper employs a…

Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current models remain severely constrained by the scarcity of…