Hierarchical Dual-Change Collaborative Learning for UAV Scene Change Captioning

• URL: http://arxiv.org/abs/2603.12832v1
• Date: Fri, 13 Mar 2026 09:33:11 GMT
• Title: Hierarchical Dual-Change Collaborative Learning for UAV Scene Change Captioning
• Abstract summary: This paper proposes a novel task for UAV scene understanding - UAV Scene Change Captioning.<n>It aims to generate natural language descriptions of semantic changes in dynamic aerial imagery captured from a movable viewpoint.
• Score: 20.801550679713568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper proposes a novel task for UAV scene understanding - UAV Scene Change Captioning (UAV-SCC) - which aims to generate natural language descriptions of semantic changes in dynamic aerial imagery captured from a movable viewpoint. Unlike traditional change captioning that mainly describes differences between image pairs captured from a fixed camera viewpoint over time, UAV scene change captioning focuses on image-pair differences resulting from both temporal and spatial scene variations dynamically captured by a moving camera. The key challenge lies in understanding viewpoint-induced scene changes from UAV image pairs that share only partially overlapping scene content due to viewpoint shifts caused by camera rotation, while effectively exploiting the relative orientation between the two images. To this end, we propose a Hierarchical Dual-Change Collaborative Learning (HDC-CL) method for UAV scene change captioning. In particular, a novel transformer, \emph{i.e.} Dynamic Adaptive Layout Transformer (DALT) is designed to adaptively model diverse spatial layouts of the image pair, where the interrelated features derived from the overlapping and non-overlapping regions are learned within the flexible and unified encoding layer. Furthermore, we propose a Hierarchical Cross-modal Orientation Consistency Calibration (HCM-OCC) method to enhance the model's sensitivity to viewpoint shift directions, enabling more accurate change captioning. To facilitate in-depth research on this task, we construct a new benchmark dataset, named UAV-SCC dataset, for UAV scene change captioning. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance on this task. The dataset and code will be publicly released upon acceptance of this paper.

Related papers

• A 2D Semantic-Aware Position Encoding for Vision Transformers [32.86183384267028]
  Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention.<n>Existing position encoding techniques, which are largely borrowed from natural language processing, fail to effectively capture semantic-aware positional relationships between image patches.<n>Traditional approaches like absolute position encoding and relative position encoding primarily focus on 1D linear position relationship, often the semantic similarity between distant yet contextually related patches.
  arXiv  Detail & Related papers  (2025-05-14T15:17:34Z)
• Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning [49.24306593078429]
  We propose a novel framework for remote sensing image change captioning, guided by Key Change Features and Instruction-tuned (KCFI) KCFI includes a ViTs encoder for extracting bi-temporal remote sensing image features, a key feature perceiver for identifying critical change areas, and a pixel-level change detection decoder. To validate the effectiveness of our approach, we compare it against several state-of-the-art change captioning methods on the LEVIR-CC dataset.
  arXiv  Detail & Related papers  (2024-09-19T09:33:33Z)
• Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance [19.663899648983417]
  We introduce a novel change captioning (CC) method based on the foundational knowledge and semantic guidance. We validate the proposed method on the LEVIR-CC and LEVIR-CD datasets.
  arXiv  Detail & Related papers  (2024-07-19T05:07:41Z)
• Image Captioning via Dynamic Path Customization [100.15412641586525]
  We propose a novel Dynamic Transformer Network (DTNet) for image captioning, which dynamically assigns customized paths to different samples, leading to discriminative yet accurate captions. To validate the effectiveness of our proposed DTNet, we conduct extensive experiments on the MS-COCO dataset and achieve new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-06-01T07:23:21Z)
• A Transformer-Based Adaptive Semantic Aggregation Method for UAV Visual Geo-Localization [2.1462492411694756]
  This paper addresses the task of Unmanned Aerial Vehicles (UAV) visual geo-localization. Part matching is crucial for UAV visual geo-localization since part-level representations can capture image details and help to understand the semantic information of scenes. We introduce a transformer-based adaptive semantic aggregation method that regards parts as the most representative semantics in an image.
  arXiv  Detail & Related papers  (2024-01-03T06:58:52Z)
• Neighborhood Contrastive Transformer for Change Captioning [80.10836469177185]
  We propose a neighborhood contrastive transformer to improve the model's perceiving ability for various changes under different scenes. The proposed method achieves the state-of-the-art performance on three public datasets with different change scenarios.
  arXiv  Detail & Related papers  (2023-03-06T14:39:54Z)
• Learning to Model Multimodal Semantic Alignment for Story Visualization [58.16484259508973]
  Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story. Current works face the problem of semantic misalignment because of their fixed architecture and diversity of input modalities. We explore the semantic alignment between text and image representations by learning to match their semantic levels in the GAN-based generative model.
  arXiv  Detail & Related papers  (2022-11-14T11:41:44Z)
• Diverse Video Captioning by Adaptive Spatio-temporal Attention [7.96569366755701]
  Our end-to-end encoder-decoder video captioning framework incorporates two transformer-based architectures. We introduce an adaptive frame selection scheme to reduce the number of required incoming frames. We estimate semantic concepts relevant for video captioning by aggregating all ground captions truth of each sample.
  arXiv  Detail & Related papers  (2022-08-19T11:21:59Z)
• Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions [78.71745819446176]
  Refign is a generic extension to self-training-based UDA methods which leverages cross-domain correspondences. Refign consists of two steps: (1) aligning the normal-condition image to the corresponding adverse-condition image using an uncertainty-aware dense matching network, and (2) refining the adverse prediction with the normal prediction using an adaptive label correction mechanism. The approach introduces no extra training parameters, minimal computational overhead -- during training only -- and can be used as a drop-in extension to improve any given self-training-based UDA method.
  arXiv  Detail & Related papers  (2022-07-14T11:30:38Z)
• Visual-aware Attention Dual-stream Decoder for Video Captioning [12.139806877591212]
  The attention mechanism in the current video captioning method learns to assign weight to each frame, promoting the decoder dynamically. This may not explicitly model the correlation and the temporal coherence of the visual features extracted in the sequence frames. We propose a new Visual-aware Attention (VA) model, which unifies changes of temporal sequence frames with the words at the previous moment. The effectiveness of the proposed Visual-aware Attention Dual-stream Decoder (VADD) is demonstrated.
  arXiv  Detail & Related papers  (2021-10-16T14:08:20Z)
• StyTr^2: Unbiased Image Style Transfer with Transformers [59.34108877969477]
  The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Traditional neural style transfer methods are usually biased and content leak can be observed by running several times of the style transfer process with the same reference image. We propose a transformer-based approach, namely StyTr2, to address this critical issue.
  arXiv  Detail & Related papers  (2021-05-30T15:57:09Z)

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.