Related papers: ICAR: Image-based Complementary Auto Reasoning

Composed image retrieval (CIR) is a vision language task that retrieves a target image using a reference image and modification text, enabling intuitive specification of desired changes. While effectively fusing visual and textual…

Vision transformers in vision-language models typically use the same amount of compute for every image, regardless of whether it is simple or complex. We propose ICAR (Image Complexity-Aware Retrieval), an adaptive computation approach that…

Composed Image Retrieval (CIR) retrieves target images using a reference image paired with modification text. Despite rapid advances, all existing methods and datasets operate at the image level -- a single reference image plus modification…

Composed image retrieval (CIR) requires multi-modal models to jointly reason over visual content and semantic modifications presented in text-image input pairs. While current CIR models achieve strong performance on common benchmark cases,…

In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To…

Composed image retrieval (CIR) aims to retrieve a target image that depicts a reference image modified by a textual description. While recent vision-language models (VLMs) achieve promising CIR performance by embedding images and text into…

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…

The field of autonomous vehicles (AVs) predominantly leverages multi-modal integration of LiDAR and camera data to achieve better performance compared to using a single modality. However, the fusion process encounters challenges in…

Multi-agent collaborative perception has emerged as a widely recognized technology in the field of autonomous driving in recent years. However, current collaborative perception predominantly relies on LiDAR point clouds, with significantly…

Humans can progressively learn visual concepts from easy to hard questions. To mimic this efficient learning ability, we propose a competence-aware curriculum for visual concept learning in a question-answering manner. Specifically, we…

Composed Image Retrieval (CIR) enables fine-grained visual search by combining a reference image with a textual modification. While supervised CIR methods achieve high accuracy, their reliance on costly triplet annotations motivates…

We propose FusionBERT, a novel multi-view visual fusion framework for image-3D multimodal retrieval. Existing image-3D representation learning methods predominantly focus on feature alignment of a single object image and its 3D model,…

Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-shot learning paradigms…

The rapid expansion of online fashion platforms has created an increasing demand for intelligent recommender systems capable of understanding both visual and textual cues. This paper proposes a hybrid multimodal deep learning framework for…

Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the desired modification. Despite the rapid development of CIR models, their performance is…

For fashion outfits to be considered aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color. Previous works have defined visual compatibility as a binary…

In natural vision, feedback connections support versatile visual inference capabilities such as making sense of the occluded or noisy bottom-up sensory information or mediating pure top-down processes such as imagination. However, the…

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if…

The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new…

Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…