Related papers: Towards Unified Token Learning for Vision-Language…
How to achieve vision-language (VL) tracking using natural language descriptions from a video sequence \textbf{without relying on any bounding-box ground truth}? In this work, we achieve this goal by tackling \textit{self-supervised VL…
Vision-Language Tracking aims to continuously localize objects described by a visual template and a language description. Existing methods, however, are typically limited to local search, making them prone to failures under viewpoint…
Single object tracking aims to locate one specific target in video sequences, given its initial state. Classical trackers rely solely on visual cues, restricting their ability to handle challenges such as appearance variations, ambiguity,…
Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…
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…
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…
Vision-language tracking has received increasing attention in recent years, as textual information can effectively address the inflexibility and inaccuracy associated with specifying the target object to be tracked. Existing works either…
Current mainstream vision-language (VL) tracking framework consists of three parts, \ie a visual feature extractor, a language feature extractor, and a fusion model. To pursue better performance, a natural modus operandi for VL tracking is…
Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus…
Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context…
UAV-ground visual tracking (UGVT) aims to simultaneously track the same object from both the UAV and the ground view. However, existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance…
One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, existing…
Visual object tracking aims to locate a targeted object in a video sequence based on an initial bounding box. Recently, Vision-Language~(VL) trackers have proposed to utilize additional natural language descriptions to enhance versatility…
Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…
With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to…
As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for…
Visual single object tracking aims to continuously localize and estimate the scale of a target in subsequent video frames, given only its initial state in the first frame. This task has traditionally been framed as a template matching…
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…
Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…
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…