Related papers: 3D CoCa v2: Contrastive Learners with Test-Time Se…
Audio-language pretraining holds promise for general-purpose audio understanding, yet remains underexplored compared to its vision counterpart. While vision-language models like CLIP serve as widely adopted foundations, existing…
Vision-language models (VLMs) have advanced rapidly, yet they still struggle with basic spatial reasoning. Despite strong performance on general benchmarks, modern VLMs remain brittle at understanding 2D spatial relationships such as…
Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on…
Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. The recent breakthrough of 2D open-vocabulary perception is largely driven by Internet-scale paired image-text data with…
Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…
Automatically generating natural language descriptions from an image is a challenging problem in artificial intelligence that requires a good understanding of the visual and textual signals and the correlations between them. The…
We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material. While other approaches find correspondences between pairs of images by treating…
This prospective study proposes CoMatch, a novel semi-dense image matcher with dynamic covisibility awareness and bilateral subpixel accuracy. Firstly, observing that modeling context interaction over the entire coarse feature map elicits…
3D scene reconstruction and understanding have gained increasing popularity, yet existing methods still struggle to capture fine-grained, language-aware 3D representations from 2D images. In this paper, we present GALA, a novel framework…
Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonomous driving, and virtual/augmented reality. However, methods…
We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal…
Image captioning is a computer vision task that involves generating natural language descriptions for images. This method has numerous applications in various domains, including image retrieval systems, medicine, and various industries.…
Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…
Image captioning is a challenging task that combines the field of computer vision and natural language processing. A variety of approaches have been proposed to achieve the goal of automatically describing an image, and recurrent neural…
We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…
This paper establishes a formal information-theoretic framework for image captioning, conceptualizing captions as compressed linguistic representations that selectively encode semantic units in images. Our framework posits that good image…
Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical entities being described. In this work, we focus on inferring…
Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban…
3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object directly, causing failure in complex scenarios. In addition, it…
Compressing videos into binary codes can improve retrieval speed and reduce storage overhead. However, learning accurate hash codes for video retrieval can be challenging due to high local redundancy and complex global dependencies between…