paper-with-me

Papers

Autoregressive Sequential Pretraining for Visual Tracking

2025-01-01 · CVPR 2025 1 · Shiyi Liang, Yifan Bai, Yihong Gong, Xing Wei

Recent advancements in visual object tracking have shifted towards a sequential generation paradigm, where object deformation and motion exhibit strong temporal dependencies. Despite the importance of these dependencies, widely adopted image-level pretrained backbones barely capture the dynamics in the consecutive video, which is the essence of tracking. Thus, we propose AutoRegressive Sequential Pretraining (ARP), an unsupervised spatio-temporal learner, via generating the evolution of object appearance and motion in video sequences.Our method leverages a diffusion model to autoregressively generate the future frame appearance, conditioned on historical embeddings extracted by a general encoder. Furthermore, to ensure trajectory coherence, the same encoder is employed to learn trajectory consistency by generating coordinate sequences in a reverse autoregressive fashion, a process we term back-tracking. Further, we integrate the pretrained ARP into ARTrackV2, creating ARPTrack, which is further fine-tuned for tracking tasks. ARPTrack achieves state-of-the-art performance across multiple benchmarks, becoming the first tracker to surpass 80% AO on GOT-10k, while maintaining high efficiency. These results demonstrate the effectiveness of our approach in capturing temporal dependencies for continuous video tracking.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectObject TrackingVisual Object TrackingVisual Tracking

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
AO This study proposes an efficient metaheuristic algorithm called the Artemisinin Optimization (AO) algorithm. This algorithm draws inspiration from the process of artemisinin…

Similar Papers 제목 키워드 기반

Visual Self-Refinement for Autoregressive Models

2025-10-01 · Jiamian Wang, Ziqi Zhou, Chaithanya Kumar Mummadi, Sohail Dianat 외 arxiv

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token predicti…

Autoregressive Visual Tracking

2023-01-01 · CVPR 2023 2023 2 · Xing Wei, Yifan Bai, Yongchao Zheng, Dahu Shi 외

We present ARTrack, an autoregressive framework for visual object tracking. ARTrack tackles tracking as a coordinate sequence interpretation task that estimates object trajectories progressively, where the current es…

ObjectObject TrackingTemplate MatchingVideo Object Tracking+2

UT5: Pretraining Non autoregressive T5 with unrolled denoising

2023-11-14 · Mahmoud G. Salem, Jiayu Ye, Chu-Cheng Lin, Frederick Liu

Recent advances in Transformer-based Large Language Models have made great strides in natural language generation. However, to decode K tokens, an autoregressive model needs K sequential forward passes, which may be a pe…

DenoisingQuestion GenerationQuestion-GenerationText Generation

TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction

2024-05-27 · Yinda Chen, Haoyuan Shi, Xiaoyu Liu, Te Shi 외

Autoregressive next-token prediction is a standard pretraining method for large-scale language models, but its application to vision tasks is hindered by the non-sequential nature of image data, leading to cumulative err…

MambaPredictionSegmentation

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

2025-12-24 · Jinghan Li, Yang Jin, Hao Jiang, Yadong Mu 외 arxiv

Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregressive (AR) generative models like GPT have revolutionized NLP, most visual …

Representation Learning