Related papers: Scale, Don't Fine-tune: Guiding Multimodal LLMs fo…

Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…

Vision-and-language pre-training (VLP) models have experienced a surge in popularity recently. By fine-tuning them on specific datasets, significant performance improvements have been observed in various tasks. However, full fine-tuning of…

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of…

Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other…

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities across a wide range of vision-language tasks. However, due to the restricted input resolutions, MLLMs face significant challenges in precisely understanding and…

Multimodal large language models~(MLLMs) have demonstrated promising spatial understanding capabilities, such as referencing and grounding object descriptions. Despite their successes, MLLMs still fall short in fine-grained spatial…

Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for emotion recognition in these models remains largely unexplored…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and…

Multimodal fusion of remote sensing images serves as a core technology for overcoming the limitations of single-source data and improving the accuracy of surface information extraction, which exhibits significant application value in fields…

Vision-language models (VLMs) classify the query video by calculating a similarity score between the visual features and text-based class label representations. Recently, large language models (LLMs) have been used to enrich the text-based…

Zero-shot Vision-and-Language Navigation (VLN) agents leveraging Large Language Models (LLMs) excel in generalization but suffer from insufficient spatial perception. Focusing on complex continuous environments, we categorize key perceptual…

Deep neural networks have achieved promising progress in remote sensing (RS) image classification, for which the training process requires abundant samples for each class. However, it is time-consuming and unrealistic to annotate labels for…

Test-time scaling (TTS) has recently emerged as a promising direction to exploit the hidden reasoning capabilities of pre-trained large language models (LLMs). However, existing scaling methods narrowly focus on the compute-optimal…

This report introduces an enhanced method for the Foundational Few-Shot Object Detection (FSOD) task, leveraging the vision-language model (VLM) for object detection. However, on specific datasets, VLM may encounter the problem where the…

Visual Place Recognition (VPR) enables robots and autonomous vehicles to identify previously visited locations by matching current observations against a database of known places. However, VPR systems face significant challenges when…

We address multi-reference visual place recognition (VPR), where reference sets captured under varying conditions are used to improve localisation performance. While deep learning with large-scale training improves robustness, increasing…

Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already…