相关论文: Grounding Everything: Emerging Localization Proper…

Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both…

Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation.…

Large-scale visual-language pre-trained models (VLPM) have proven their excellent performance in downstream object detection for natural scenes. However, zero-shot nuclei detection on H\&E images via VLPMs remains underexplored. The large…

Vision language models (VLMs) like CLIP show stellar zero-shot capability on classification benchmarks. However, selecting the VLM with the highest performance on the unlabeled downstream task is non-trivial. Existing VLM selection methods…

Understanding complex human activities demands the ability to decompose motion into fine-grained, semantic-aligned sub-actions. This motion grounding process is crucial for behavior analysis, embodied AI and virtual reality. Yet, most…

Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for…

Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited performance in instance-level tasks that demand precise…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Open-vocabulary segmentation poses significant challenges, as it requires segmenting and recognizing objects across an open set of categories in unconstrained environments. Building on the success of powerful vision-language (ViL)…

The goal of this paper is to extract the visual-language correspondence from a pre-trained text-to-image diffusion model, in the form of segmentation map, i.e., simultaneously generating images and segmentation masks for the corresponding…

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

In this paper, we present GEM as a General Evaluation benchmark for Multimodal tasks. Different from existing datasets such as GLUE, SuperGLUE, XGLUE and XTREME that mainly focus on natural language tasks, GEM is a large-scale…

The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large,…

We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data…

Recent advances in Vision Language Models (VLMs) and Vision Foundation Models (VFMs) have opened new opportunities for zero-shot text-guided segmentation of remote sensing imagery. However, most existing approaches still rely on additional…

While recent vision-and-language models (VLMs) like CLIP are a powerful tool for analyzing text and images in a shared semantic space, they do not explicitly model the hierarchical nature of the set of texts which may describe an image.…

The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow…

The ability to segment objects based on open-ended language prompts remains a critical challenge, requiring models to ground textual semantics into precise spatial masks while handling diverse and unseen categories. We present OpenWorldSAM,…

Vision-language pre-training (VLP) has shown impressive performance on a wide range of cross-modal tasks, where VLP models without reliance on object detectors are becoming the mainstream due to their superior computation efficiency and…