VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking

• URL: http://arxiv.org/abs/2605.04574v1
• Date: Wed, 06 May 2026 07:23:53 GMT
• Title: VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking
• Abstract summary: UAV-ground visual tracking (UGVT) aims to simultaneously track the same object from both the UAV and the ground view.<n>Existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance matching.<n>We propose VL-UniTrack, a fully unified framework enhanced by visual-language prompts.
• Score: 35.96855931247585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: UAV-ground visual tracking (UGVT) aims to simultaneously track the same object from both the UAV and the ground view. However, existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance matching, which struggles to establish reliable correspondence under drastic view differences, leading to tracking unreliability. To address these limitations, we propose VL-UniTrack, a fully unified framework enhanced by visual-language prompts. By encoding features from both views within a single shared encoder, our method breaks the barrier of feature isolation to facilitate sufficient cross-view interaction. To overcome the ambiguity caused by relying solely on appearance matching, we design visual-language geometric prompting module, which fuses language descriptions with visual features to generate learnable prompts. These prompts are then fed into our prompt-guided cross-view adapter module to enable sufficient cross-view feature interaction and to guide the learning of view-specific feature representations. Furthermore, a confidence-modulated mutual distillation loss is proposed to regularize the training by mitigating noise propagation. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the latest benchmark. The code can be downloaded in https://github.com/xuboyue1999/VL-UniTrack.git

Related papers

• OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection [9.87006529425909]
  We present OPUS, a unified detector supporting text, interactive visual, generic visual, and mixed prompting within one framework.<n> OPUS achieves state-of-the-art Visual-I performance, reaching 68.1/69.2/54.7 AP, while maintaining balanced Text and Visual-G accuracy.
  arXiv  Detail & Related papers  (2026-08-31T04:57:12Z)
• View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification [43.69772242567068]
  ViSA is a view-aware framework that achieves cross-view semantic consistency.<n>ViSA consistently achieves superior performance, with a notable 10.06% mAP improvement on the challenging CARGO cross-view protocol.
  arXiv  Detail & Related papers  (2026-05-18T10:32:26Z)
• Unleashing Vision-Language Semantics for Deepfake Video Detection [78.7562836979696]
  Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities in detecting artifacts across different identities.<n>We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection.
  arXiv  Detail & Related papers  (2026-03-25T16:05:35Z)
• Dual Prompt-Driven Feature Encoding for Nighttime UAV Tracking [7.916061194416488]
  This work proposes a dual prompt-driven feature encoding method that integrates prompt-conditioned feature adaptation and context-aware prompt evolution.<n>Experiments validate the effectiveness of the proposed dual prompt-driven tracker (DPTracker) in tackling nighttime UAV tracking.
  arXiv  Detail & Related papers  (2026-03-20T04:16:39Z)
• VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning [69.64660280965971]
  VideoAnchor is a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining.<n>We show consistent performance gains on benchmarks with InternVL2-8B and Q2.5VL-72B.<n>Our codes will be made public at https://github.com/feufhd/VideoAnchor.
  arXiv  Detail & Related papers  (2025-09-29T17:54:04Z)
• Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation [120.23172120151821]
  We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models.<n>We introduce an automated pipeline that constructs image pairs with annotated semantic and visual correspondences.<n>We propose a new metric, Visual Semantic Matching, that quantifies visual inconsistencies in subject-driven image generation.
  arXiv  Detail & Related papers  (2025-09-26T07:11:55Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• Just Functioning as a Hook for Two-Stage Referring Multi-Object Tracking [22.669740476582835]
  Referring Multi-Object Tracking aims to localize target trajectories in videos specified by natural language expressions.<n>We present a systematic analysis of the intrinsic relationship between the two subtasks of tracking and referring in RMOT.<n>We propose JustHook, a novel two-stage RBT framework where a Hook module is firstly designed to redefine the linkage between subtasks.
  arXiv  Detail & Related papers  (2025-03-10T16:38:42Z)
• UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models [23.044366104080822]
  We introduce textbfUniRS, the first vision-language model bftextremote bftextsensing tasks across various types of visual input.<n>UniRS supports single images, dual-time image pairs, and videos as input, enabling comprehensive remote sensing temporal analysis.<n> Experimental results show that UniRS achieves state-of-the-art performance across diverse tasks.
  arXiv  Detail & Related papers  (2024-12-30T06:34:18Z)
• Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking [3.416427651955299]
  Single object tracking aims to locate one specific target in video sequences, given its initial state. Vision-Language (VL) tracking has emerged as a promising approach. We present a novel tracker that progressively explores target-centric semantics for VL tracking.
  arXiv  Detail & Related papers  (2023-11-28T02:28:12Z)
• Exploring Part-Informed Visual-Language Learning for Person Re-Identification [52.92511980835272]
  We propose Part-Informed Visual-language Learning ($pi$-VL) to enhance fine-grained visual features with part-informed language supervisions for ReID tasks.<n>$pi$-VL introduces a human parsing-guided prompt tuning strategy and a hierarchical visual-language alignment paradigm to ensure within-part feature semantic consistency.<n>As a plug-and-play and inference-free solution, our $pi$-VL achieves performance comparable to or better than state-of-the-art methods on four commonly used ReID benchmarks.
  arXiv  Detail & Related papers  (2023-08-04T23:13:49Z)

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.