Related papers: Serial Over Parallel: Learning Continual Unificati…
Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference…
Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that…
Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing…
In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object…
The development of smart cities has led to the generation of massive amounts of multi-modal data in the context of a range of tasks that enable a comprehensive monitoring of the smart city infrastructure and services. This paper surveys one…
Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing methods often train separate models for each modality or rely on pretrained models to adapt…
As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not…
Path planning for autonomous search and tracking of multiple objects is a critical problem in applications such as reconnaissance, surveillance, and data gathering. Due to the inherent competing objectives of searching for new objects while…
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting…
Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from…
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects. Most current approaches for…
We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation. The…
We present UniTrack, a plug-and-play graph-theoretic loss function designed to significantly enhance multi-object tracking (MOT) performance by directly optimizing tracking-specific objectives through unified differentiable learning. Unlike…
Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX). Due to the gap…
Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem…
Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation…
Object detection has long been a topic of high interest in computer vision literature. Motivated by the fact that annotating data for the multi-object tracking (MOT) problem is immensely expensive, recent studies have turned their attention…
Multi-modal industrial anomaly detection typically relies on separate models for each product category, fundamentally limiting practical scalability. When shifting to a unified paradigm that handles diverse classes simultaneously, detection…
Visual Object Tracking (VOT) aims to estimate the positions of target objects in a video sequence, which is an important vision task with various real-world applications. Depending on whether the initial states of target objects are…
With the rapid advancement of remote sensing technology, high-resolution multi-modal imagery is now more widely accessible. Conventional Object detection models are trained on a single dataset, often restricted to a specific imaging…