Related papers: Exploiting Multimodal Spatial-temporal Patterns fo…
With efficient appearance learning models, Discriminative Correlation Filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major…
Skeleton-based action recognition faces two longstanding challenges: the scarcity of labeled training samples and difficulty modeling short- and long-range temporal dependencies. To address these issues, we propose a unified framework,…
Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches incorporate the geometric effect of object- and ego motion…
Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning…
Reliable forecasting of traffic flow requires efficient modeling of traffic data. Indeed, different correlations and influences arise in a dynamic traffic network, making modeling a complicated task. Existing literature has proposed many…
Accurate travel time estimation (TTE) plays a crucial role in intelligent transportation systems. However, it remains challenging due to heterogeneous data sources and complex traffic dynamics. Moreover, traditional approaches typically…
4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal…
Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…
Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is…
Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements, current methods easily suffer the distractors or heavy object appearance variations in…
Spatio-temporal graph (STG) forecasting is a critical task with extensive applications in the real world, including traffic and weather forecasting. Although several recent methods have been proposed to model complex dynamics in STGs,…
Human-centric traffic signal control in corridor networks must increasingly account for multimodal travelers, particularly high-occupancy public transportation, rather than focusing solely on vehicle-centric performance. This paper proposes…
Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal…
Multi-modal behaviors exhibited by surrounding vehicles (SVs) can typically lead to traffic congestion and reduce the travel efficiency of autonomous vehicles (AVs) in dense traffic. This paper proposes a real-time parallel trajectory…
Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which…
Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for video understanding. In this work, we explore higher-order STSS and demonstrate how STSSs…
The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across…
In the realm of video object tracking, auxiliary modalities such as depth, thermal, or event data have emerged as valuable assets to complement the RGB trackers. In practice, most existing RGB trackers learn a single set of parameters to…
A comprehensive understanding of surgical scenes allows for monitoring of the surgical process, reducing the occurrence of accidents and enhancing efficiency for medical professionals. Semantic modeling within operating rooms, as a scene…
A main challenge of Visual-Language Tracking (VLT) is the misalignment between visual inputs and language descriptions caused by target movement. Previous trackers have explored many effective feature modification methods to preserve more…