Related papers: MLS-Track: Multilevel Semantic Interaction in RMOT
Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of…
Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more…
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. However, due to unreliable detection, occlusion and fast…
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-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It…
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection.This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this…
Open-world interactive object search in household environments requires understanding semantic relationships between objects and their surrounding context to guide exploration efficiently. Prior methods either rely on vision-language…
Current multi-object tracking (MOT) aims to predict trajectories of targets (i.e., ''where'') in videos. Yet, knowing merely ''where'' is insufficient in many crucial applications. In comparison, semantic understanding such as fine-grained…
Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level…
Object referring has important applications, especially for human-machine interaction. While having received great attention, the task is mainly attacked with written language (text) as input rather than spoken language (speech), which is…
Conversational Recommender Systems (CRSs) aim to provide personalized recommendations by interacting with users through conversations. Most existing studies of CRS focus on extracting user preferences from conversational contexts. However,…
The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segmentation masks by…
RGB-Thermal (RGBT) tracking aims to achieve robust object localization across diverse environmental conditions by fusing visible and thermal infrared modalities. However, existing RGBT trackers rely solely on initial-frame visual…
Multimodal large language models (MLLMs) are rapidly evolving, presenting increasingly complex safety challenges. However, current dataset construction methods, which are risk-oriented, fail to cover the growing complexity of real-world…
Solving complex real-world tasks, e.g., autonomous fleet control, often involves a coordinated team of multiple agents which learn strategies from visual inputs via reinforcement learning. Many existing multi-agent reinforcement learning…
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…
Referring expressions usually describe an object using properties of the object and relationships of the object with other objects. We propose a technique that integrates context between objects to understand referring expressions. Our…
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…
Vision sensors are becoming more important in Intelligent Transportation Systems (ITS) for traffic monitoring, management, and optimization as the number of network cameras continues to rise. However, manual object tracking and matching…
Current multi-object tracking (MOT) algorithms typically overlook issues inherent in low-quality videos, leading to significant degradation in tracking performance when confronted with real-world image deterioration. Therefore, advancing…