paper-with-me

Papers

Autoregressive Visual Tracking

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

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 estimate is induced by previous states and in turn affects subsequences. This time-autoregressive approach models the sequential evolution of trajectories to keep tracing the object across frames, making it superior to existing template matching based trackers that only consider the per-frame localization accuracy. ARTrack is simple and direct, eliminating customized localization heads and post-processings. Despite its simplicity, ARTrack achieves state-of-the-art performance on prevailing benchmark datasets.

📄 PDF Abstract BibTeX

Code (1)

miv-xjtu/artrack 공식 구현 pytorch

Tasks

ObjectObject TrackingTemplate MatchingVideo Object TrackingVisual Object TrackingVisual Tracking

Similar Papers 제목 키워드 기반

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 dependenc…

ObjectObject TrackingVisual Object TrackingVisual Tracking

Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers

2024-03-15 · Jinxia Xie, Bineng Zhong, Zhiyi Mo, Shengping Zhang 외

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio…

Visual Object TrackingVisual Tracking

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

2024-01-01 · CVPR 2024 1 · Jinxia Xie, Bineng Zhong, Zhiyi Mo, Shengping Zhang 외

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However most top-performing tracking algorithms rely on many hand-crafted components for spa…

Visual Tracking

Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking

2023-04-27 · CVPR 2023 1 · Xin Chen, Ben Kang, Jiawen Zhu, Dong Wang 외

In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generatio…

DecoderObjectObject TrackingRgb-T Tracking+2

FARTrack: Fast Autoregressive Visual Tracking with High Performance

2026-02-03 · Guijie Wang, Tong Lin, Yifan Bai, Anjia Cao 외 arxiv

Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deplo…

Model CompressionVisual Tracking