Related papers: Type-to-Track: Retrieve Any Object via Prompt-base…
Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for…
The ability to recognize, localize and track dynamic objects in a scene is fundamental to many real-world applications, such as self-driving and robotic systems. Yet, traditional multiple object tracking (MOT) benchmarks rely only on a few…
Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions,…
Multi-object tracking is a fundamental vision problem that has been studied for a long time. As deep learning brings excellent performances to object detection algorithms, Tracking by Detection (TBD) has become the mainstream tracking…
Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment…
Multimodal semantic cues, such as textual descriptions, have shown strong potential in enhancing target perception for tracking. However, existing methods rely on static textual descriptions from large language models, which lack…
Open-vocabulary multi-object tracking (OVMOT) represents a critical new challenge involving the detection and tracking of diverse object categories in videos, encompassing both seen categories (base classes) and unseen categories (novel…
Multi-object tracking (MOT) has traditionally focused on estimating trajectories of all objects in a video, without selectively reasoning about user-specified targets under semantic instructions. In this work, we introduce a query-driven…
Multi-Object Tracking (MOT) has been a long-standing challenge in video understanding. A natural and intuitive approach is to split this task into two parts: object detection and association. Most mainstream methods employ meticulously…
The new trend in multi-object tracking task is to track objects of interest using natural language. However, the scarcity of paired prompt-instance data hinders its progress. To address this challenge, we propose a high-quality yet low-cost…
Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…
Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous…
The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit…
Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between…
Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…
Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods…
Most existing video moment retrieval methods rely on temporal sequences of frame- or clip-level features that primarily encode global visual and semantic information. However, such representations often fail to capture fine-grained object…
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field. Most existing approaches are not able to properly handle multi-object tracking challenges such as…
Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking. However, progress has been limited by the lack of comprehensive multi-view…