FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking

• URL: http://arxiv.org/abs/2608.09369v1
• Date: Mon, 10 Aug 2026 09:48:11 GMT
• Title: FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking
• Abstract summary: We propose a visual-cortex-inspired framework that introduces sparse, group-level layer-aligned cross-frame feedback into pretrained Transformer trackers.<n>Previous-frame intermediate states are detached, cached, and returned to corresponding Transformer groups in the current frame.
• Score: 5.3452643825668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates, prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate corresponding processing stages. We propose \textbf{FeedbackTrack}, a visual-cortex-inspired framework that introduces sparse, group-level layer-aligned cross-frame feedback into pretrained Transformer trackers. Previous-frame intermediate states are detached, cached, and returned to corresponding Transformer groups in the current frame through two lightweight pathways: Query Feedback for token-level query modulation and Gate Feedback for context-dependent feature modulation. FeedbackTrack preserves the original tracking pipeline with only a fixed-size one-frame cache. Across SPMTrack and ARTrackV2, FeedbackTrack consistently improves five backbone configurations on LaSOT and GOT-10k, achieving 83.4 AO and 79.1 AUC with SPMTrack-G while adding less than 1\% parameters. Controlled comparisons show that cross-frame feedback outperforms same-frame modulation by 1.8--3.2 AO points, demonstrating that the gains mainly come from recurrent historical information. Further analysis reveals a non-uniform depth-dependent organization of learned feedback strengths, highlighting the effectiveness of recurrent feedback for Transformer tracking.

Related papers

• SwiTrack: Tri-State Switch for Cross-Modal Object Tracking [74.15663758681849]
  Cross-modal object tracking (CMOT) is an emerging task that maintains target consistency while the video stream switches between different modalities.<n>We propose SwiTrack, a novel state-switching framework that redefines CMOT through the deployment of three specialized streams.
  arXiv  Detail & Related papers  (2025-11-20T10:52:54Z)
• Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking [54.124445709376154]
  We propose a novel asymmetric Siamese tracker named textbfAsymTrack for efficient tracking.<n>Building on this architecture, we devise an efficient template modulation mechanism to inject crucial cues into the search features.<n>Experiments demonstrate that AsymTrack offers superior speed-precision trade-offs across different platforms.
  arXiv  Detail & Related papers  (2025-03-01T14:44:54Z)
• Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers [55.46413719810273]
  rich-temporal information is crucial to the complicated target appearance in visual tracking. Our method improves the tracker's performance on six popular tracking benchmarks.
  arXiv  Detail & Related papers  (2024-03-15T02:39:26Z)
• ProContEXT: Exploring Progressive Context Transformer for Tracking [20.35886416084831]
  Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between frames. We revamped the framework with Progressive Context. Transformer Tracker (ProContEXT), which coherently exploits spatial and temporal contexts to predict object motion trajectories.
  arXiv  Detail & Related papers  (2022-10-27T14:47:19Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)
• Context-aware Visual Tracking with Joint Meta-updating [11.226947525556813]
  We propose a context-aware tracking model to optimize the tracker over the representation space, which jointly meta-update both branches by exploiting information along the whole sequence. The proposed tracking method achieves an EAO score of 0.514 on VOT2018 with the speed of 40FPS, demonstrating its capability of improving the accuracy and robustness of the underlying tracker with little speed drop.
  arXiv  Detail & Related papers  (2022-04-04T14:16:00Z)
• Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking [69.08903927311283]
  Existing tracking approaches rely on customized sub-modules and need prior knowledge for architecture selection. This paper presents a simplified tracking architecture (SimTrack) by leveraging a transformer backbone for joint feature extraction and interaction. Our SimTrack improves the baseline with 2.5%/2.6% AUC gains on LaSOT/TNL2K and gets results competitive with other specialized tracking algorithms without bells and whistles.
  arXiv  Detail & Related papers  (2022-03-10T12:20:58Z)
• Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking [82.34356879078955]
  We propose a compact memory embedding to enhance the discrimination of the segmentation-based deformable visual tracking method. Our method outperforms the excellent segmentation-based trackers, i.e., D3S and SiamMask on DAVIS 2017 benchmark.
  arXiv  Detail & Related papers  (2021-11-23T03:07:12Z)
• TrTr: Visual Tracking with Transformer [29.415900191169587]
  We propose a novel tracker network based on a powerful attention mechanism called Transformer encoder-decoder architecture. We design the classification and regression heads using the output of Transformer to localize target based on shape-agnostic anchor. Our method performs favorably against state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-05-09T02:32:28Z)
• Target Transformed Regression for Accurate Tracking [30.516462193231888]
  This paper repurposes a Transformer-alike regression branch, termed as Target Transformed Regression (TREG) for accurate anchor-free tracking. The core to our TREG is to model pair-wise relation between elements in target template and search region, and use the resulted target enhanced visual representation for accurate bounding box regression. In addition, we devise a simple online template update mechanism to select reliable templates, increasing the robustness for appearance variations and geometric deformations of target in time.
  arXiv  Detail & Related papers  (2021-04-01T11:25:23Z)

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.