Pith. sign in

REVIEW 6 cited by

R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.21980 v3 pith:QQTOU2CV submitted 2025-06-27 cs.CV

classification cs.CV
keywords trackingr1-trackmllmsmodelsqwen2visualachievedcapabilities
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 problem, evolving through major phases including correlation filters, two-stream networks, and one-stream networks with significant progress achieved. However, these methods typically require explicit classification and regression modeling, depend on supervised training with large-scale datasets, and are limited to the single task of tracking, lacking flexibility. In recent years, multi-modal large language models (MLLMs) have advanced rapidly. Open-source models like Qwen2.5-VL, a flagship MLLMs with strong foundational capabilities, demonstrate excellent performance in grounding tasks. This has spurred interest in applying such models directly to visual tracking. However, experiments reveal that Qwen2.5-VL struggles with template matching between image pairs (i.e., tracking tasks). Inspired by deepseek-R1, we fine-tuned Qwen2.5-VL using the group relative policy optimization (GRPO) reinforcement learning method on a small-scale dataset with a rule-based reward function. The resulting model, R1-Track, achieved notable performance on the GOT-10k benchmark. R1-Track supports flexible initialization via bounding boxes or text descriptions while retaining most of the original model's general capabilities. And we further discuss potential improvements for R1-Track. This rough technical report summarizes our findings as of May 2025.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.

  2. Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    D³ETOR combines debate-enhanced pseudo labeling from SAM with frequency-aware progressive debiasing in FADeNet to achieve state-of-the-art weakly-supervised camouflaged object detection using scribbles.

  3. Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    A language dependency parsing mechanism combined with Qwen-VL enables adaptive updates to textual descriptions for improved vision-language tracking performance on benchmarks like TNL2K and LaSOT.

  4. INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    INTENT mitigates cross-modal correspondence noise and modality-inherent noise in composed image retrieval via FFT-based visual invariant composition and bi-objective discriminative learning.

  5. ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    ReTrack calibrates directional bias in composed video features using semantic disentanglement and bidirectional evidence alignment to improve retrieval performance on CVR and CIR tasks.

  6. OneThinker: All-in-one Reasoning Model for Image and Video

    cs.CV 2025-12 unverdicted novelty 5.0 of 10

    OneThinker unifies image and video reasoning in one model across 10 tasks via a 600k corpus, CoT-annotated SFT, and EMA-GRPO reinforcement learning, reporting strong results on 31 benchmarks plus some cross-task transfer.

Pith tools