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

• URL: http://arxiv.org/abs/2506.21980v3
• Date: Tue, 22 Jul 2025 15:39:40 GMT
• Title: R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning
• Authors: Biao Wang, Wenwen Li, Jiawei Ge,
• Abstract summary: Single object tracking aims to continuously localize and estimate the scale of a target in subsequent video frames.<n>Qwen2.5-VL struggles with template matching between image pairs.<n>Inspired by deep-seek-R1, we fine-tuned Qwen2.5-VL using the group relative policy optimization (GRPO) reinforcement learning method.<n>The resulting model, R1-Track, achieved notable performance on the GOT-10k benchmark.
• Score: 5.59181512260003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation [67.1520483301709]
  CronusVLA is a unified framework that extends single-frame VLA models to the multi-frame paradigm through an efficient post-training stage.<n>CronusVLA achieves state-of-the-art performance on SimplerEnv with 70.9% success rate, and 12.7% improvement over OpenVLA on LIBERO.
  arXiv  Detail & Related papers  (2025-06-24T17:30:27Z)
• Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning [3.364797975300393]
  We present Observe-R1, a novel framework aimed at enhancing the reasoning capabilities of multimodal large language models (MLLMs)<n>We construct the NeuraLadder dataset, which is organized and sampled according to the difficulty and complexity of data samples for RL training.<n>Experiments with the Qwen2.5-VL-3B and Qwen2.5-VL-7B models on 20k samples from the NeuraLadder dataset show that Observe-R1 outperforms a series of larger reasoning models on both reasoning and general benchmarks.
  arXiv  Detail & Related papers  (2025-05-18T14:08:03Z)
• Compile Scene Graphs with Reinforcement Learning [69.36723767339001]
  Next-token prediction is the fundamental principle for training large language models (LLMs)<n>We introduce R1-SGG, a multimodal LLM (M-LLM) initially trained via supervised fine-tuning (SFT) on the scene graph dataset.<n>We design a set of graph-centric rewards, including three recall-based variants -- Hard Recall, Hard Recall+Relax, and Soft Recall.
  arXiv  Detail & Related papers  (2025-04-18T10:46:22Z)
• NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models [38.41524186248607]
  We introduce NV-Embed, incorporating architectural designs, training procedures, and curated datasets.<n>For model architecture, we propose a latent attention layer to obtain pooled embeddings.<n>For training algorithm, we introduce a two-stage contrastive instruction-tuning method.
  arXiv  Detail & Related papers  (2024-05-27T17:59:45Z)
• Towards Unified Token Learning for Vision-Language Tracking [65.96561538356315]
  We present a vision-language (VL) tracking pipeline, termed textbfMMTrack, which casts VL tracking as a token generation task. Our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target.
  arXiv  Detail & Related papers  (2023-08-27T13:17:34Z)
• Simple Cues Lead to a Strong Multi-Object Tracker [3.7189423451031356]
  We propose a new type of tracking-by-detection (TbD) for Multi-Object Tracking. We show that a combination of our appearance features with a simple motion model leads to strong tracking results. Our tracker generalizes to four public datasets, namely MOT17, MOT20, BDD100k, and DanceTrack, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-06-09T17:55:51Z)
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework [76.70603443624012]
  We propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k.
  arXiv  Detail & Related papers  (2022-03-22T18:37:11Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.