arXiv Computation and Language
Referring Multi-Object Tracking with Diverse Dynamic Expressions
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computer Vision
Sep 3
YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification
YesTrack introduces a two‑stage referring multi‑object tracking approach that treats the task as a discriminative Yes/No verification problem, directly using multimodal large language models (MLLMs) without generating captions. It adds lightweight temporal consistency constraints—Temporal Confidence Prior (TCP) and Temporal Reference Propagation (TRP)—to improve reliability and efficiency. The method also extends to generic multi‑object tracking as YesTrack‑MOT, achieving state‑of‑the‑art performance on Refer‑KITTI datasets while remaining efficient even with the smallest Qwen3‑VL variant.
arXiv Computer Vision
4d ago
ReferFlow: Beyond Final-Target Localization for Complex Referring Expressions
arXiv:2610.20352v1 Announce Type: new Abstract: Multimodal Large Language Models have made significant progress in referring expression comprehension (REC), yet most REC benchmarks still focus on fin...
arXiv Computer Vision
Sep 1
Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking
arXiv:2608.29126v1 Announce Type: new Abstract: Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual...
arXiv Computer Vision
Aug 25
Motion-Aware Vision-Reference Alignment for Referring Multi-Object Tracking
arXiv:2511.17681v2 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal...
Hugging Face Trending Papers
Aug 17
Unlocking Motion in Expressions: Temporal Calibration for Referring Video Object Segmentation
Referring Video Object Segmentation (RVOS) aims to segment referred objects at the pixel level in video sequences based on natural language descriptions. Existing methods typically introduce motion information within a unified cross-modal temporal modeling framework, where language cues are used for target localization and segmentation.
arXiv AI
Jun 2
CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects
arXiv:2510. 14904v4 Announce Type: replace-cross Abstract: Dense Video Object Captioning (DVOC) is the task of jointly detecting, tracking, and captioning object trajectories in a video, requiring the ability to understand spatio-temporal details and describe them in natural language.