Imagine How To Change: Explicit Procedure Modeling for Change Captioning

• URL: http://arxiv.org/abs/2603.05969v1
• Date: Fri, 06 Mar 2026 07:05:39 GMT
• Title: Imagine How To Change: Explicit Procedure Modeling for Change Captioning
• Abstract summary: Existing methods operate on static image pairs, ignoring the rich temporal dynamics of the change procedure.<n>We introduce ProCap, a novel framework that reformulates change modeling from static image comparison to dynamic procedure modeling.
• Score: 18.938737195128347
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Change captioning generates descriptions that explicitly describe the differences between two visually similar images. Existing methods operate on static image pairs, thus ignoring the rich temporal dynamics of the change procedure, which is the key to understand not only what has changed but also how it occurs. We introduce ProCap, a novel framework that reformulates change modeling from static image comparison to dynamic procedure modeling. ProCap features a two-stage design: The first stage trains a procedure encoder to learn the change procedure from a sparse set of keyframes. These keyframes are obtained by automatically generating intermediate frames to make the implicit procedural dynamics explicit and then sampling them to mitigate redundancy. Then the encoder learns to capture the latent dynamics of these keyframes via a caption-conditioned, masked reconstruction task. The second stage integrates this trained encoder within an encoder-decoder model for captioning. Instead of relying on explicit frames from the previous stage -- a process incurring computational overhead and sensitivity to visual noise -- we introduce learnable procedure queries to prompt the encoder for inferring the latent procedure representation, which the decoder then translates into text. The entire model is then trained end-to-end with a captioning loss, ensuring the encoder's output is both temporally coherent and captioning-aligned. Experiments on three datasets demonstrate the effectiveness of ProCap. Code and pre-trained models are available at https://github.com/BlueberryOreo/ProCap

Related papers

• Imagine Before You Draw: Visual Prompt Engineering for Image Generation [67.81347924426714]
  We propose Visual Prompt Engineering (VPE), which can be seamlessly integrated into internal frameworks.<n>We validate VPE across class-conditional generation, text-to-image generation, and image editing.<n>Results show that VPE can accelerate convergence, raise quality ceilings, and through internal integration, achieve substantially better editing preservation.
  arXiv  Detail & Related papers  (2026-06-03T05:01:36Z)
• Progress-Aware Video Frame Captioning [55.23366888264651]
  We propose ProgressCaptioner, a captioning model designed to capture the fine-grained temporal dynamics within an action sequence.<n>We develop the FrameCap dataset to support training and the FrameCapEval benchmark to assess caption quality.<n>Results demonstrate that ProgressCaptioner significantly surpasses leading captioning models.
  arXiv  Detail & Related papers  (2024-12-03T01:21:28Z)
• Text-based Talking Video Editing with Cascaded Conditional Diffusion [31.194060914767896]
  Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos. Previous works either require minutes of talking-face video training data and expensive test-time optimization for customized talking video editing. We propose an efficient cascaded conditional diffusion-based framework, which consists of two stages: audio to dense-landmark motion and motion to video.
  arXiv  Detail & Related papers  (2024-07-20T10:55:19Z)
• CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression [15.819672238043786]
  We propose a stereo image compression framework, named CAMSIC.<n>CAMSIC transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model.<n> Experiments show that our framework achieves state-of-the-art rate-distortion performance.
  arXiv  Detail & Related papers  (2024-03-13T13:12:57Z)
• Concatenated Masked Autoencoders as Spatial-Temporal Learner [6.475592804311682]
  We introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning. We propose a new data augmentation strategy, Video-Reverse (ViRe), which uses reversed video frames as the model's reconstruction targets.
  arXiv  Detail & Related papers  (2023-11-02T03:08:26Z)
• DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training [73.74291217502928]
  We propose a simple framework, named DeCap, for zero-shot captioning. We introduce a lightweight visual-aware language decoder. We project the visual embedding into the CLIP text embedding space, while the projected embedding retains the information of the visual input.
  arXiv  Detail & Related papers  (2023-03-06T11:02:47Z)
• Zero-Shot Video Captioning with Evolving Pseudo-Tokens [79.16706829968673]
  We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Our experiments show that the generated captions are coherent and display a broad range of real-world knowledge.
  arXiv  Detail & Related papers  (2022-07-22T14:19:31Z)
• MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining [68.05105411320842]
  We propose a novel approach MaskOCR to unify vision and language pre-training in the classical encoder-decoder recognition framework. We adopt the masked image modeling approach to pre-train the feature encoder using a large set of unlabeled real text images. We transform text data into synthesized text images to unify the data modalities of vision and language, and enhance the language modeling capability of the sequence decoder.
  arXiv  Detail & Related papers  (2022-06-01T08:27:19Z)
• Context Autoencoder for Self-Supervised Representation Learning [64.63908944426224]
  We pretrain an encoder by making predictions in the encoded representation space. The network is an encoder-regressor-decoder architecture. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks.
  arXiv  Detail & Related papers  (2022-02-07T09:33:45Z)
• 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)
• Enhanced Modality Transition for Image Captioning [51.72997126838352]
  We build a Modality Transition Module (MTM) to transfer visual features into semantic representations before forwarding them to the language model. During the training phase, the modality transition network is optimised by the proposed modality loss. Experiments have been conducted on the MS-COCO dataset demonstrating the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2021-02-23T07:20:12Z)

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.