相关论文: LG-Gaze: Learning Geometry-aware Continuous Prompt…

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global…

Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight…

Following the gaze of people inside videos is an important signal for understanding people and their actions. In this paper, we present an approach for following gaze across views by predicting where a particular person is looking…

Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate…

Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

Medical reports with substantial information can be naturally complementary to medical images for computer vision tasks, and the modality gap between vision and language can be solved by vision-language matching (VLM). However, current…

Vision-Language Models (VLMs) have made striking progress, yet their spatial reasoning remains fragile: models that answer an original input correctly can still fail under paired transformations with predictable answer mappings, revealing a…

Category-level 6D object pose estimation aims to estimate the rotation, translation and size of unseen instances within specific categories. In this area, dense correspondence-based methods have achieved leading performance. However, they…

As large language models (LLMs) have gained popularity for a variety of use cases, making them adaptable and controllable has become increasingly important, especially for user-facing applications. While the existing literature on LLM…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

Cross-View Geo-Localization (CVGL) focuses on identifying correspondences between images captured from distinct perspectives of the same geographical location. However, existing CVGL approaches are typically restricted to a single view or…

The variance in class-wise sample sizes within long-tailed scenarios often results in degraded performance in less frequent classes. Fortunately, foundation models, pre-trained on vast open-world datasets, demonstrate strong potential for…

Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…

In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly…

Feed-forward surround-view autonomous driving scene reconstruction offers fast, generalizable inference ability, which faces the core challenge of ensuring generalization while elevating novel view quality. Due to the surround-view with…

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in…

Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suffer from two limitations: (i) Geometric Ambiguity: Their…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…