相关论文: AMIGO: Agentic Multi-Image Grounding Oracle Benchm…

Image captioning is a critical task at the intersection of computer vision and natural language processing, with wide-ranging applications across various domains. For complex tasks such as diagnostic report generation, deep learning models…

Long-horizon robotic manipulation poses significant challenges for autonomous systems, requiring extended reasoning, precise execution, and robust error recovery across complex sequential tasks. Current approaches, whether based on static…

Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in recoverable observations…

Although current large Vision-Language Models (VLMs) have advanced in multimodal understanding and reasoning, their fundamental perceptual and reasoning abilities remain limited. Specifically, even on simple jigsaw tasks, existing VLMs…

There has been significant progress in creating machine learning models that identify objects in scenes along with their associated attributes and relationships; however, there is a large gap between the best models and human capabilities.…

Video mosaicking requires the registration of overlapping frames located at distant timepoints in the sequence to ensure global consistency of the reconstructed scene. However, fully automated registration of such long-range pairs is (i)…

Vision-Language Models (VLMs) have demonstrated impressive world knowledge across a wide range of tasks, making them promising candidates for embodied reasoning applications. However, existing benchmarks primarily evaluate the embodied…

Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance. Specifically, the semantic ambiguity means that some…

Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the…

The growing reproducibility crisis in machine learning has brought forward a need for careful examination of research findings. This paper investigates the claims made by Lei et al. (2023) regarding their proposed method, LICO, for…

A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We…

We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation framework [30], where each word of a given caption is paired with a mouse…

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

The frontier of visual reasoning is shifting toward models like OpenAI o3, which can intelligently create and operate tools to transform images for problem-solving, also known as thinking-\textit{with}-images in chain-of-thought. Yet…

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as…

Egocentric interaction perception is one of the essential branches in investigating human-environment interaction, which lays the basis for developing next-generation intelligent systems. However, existing egocentric interaction…

Referring-based Video Object Segmentation is a multimodal problem that requires producing fine-grained segmentation results guided by external cues. Traditional approaches to this task typically involve training specialized models, which…

Visual Grounding (VG) aims to utilize given natural language queries to locate specific target objects within images. While current transformer-based approaches demonstrate strong localization performance in standard scene (i.e, scenarios…

Image quality assessment (IQA) is inherently complex, as it reflects both the quantification and interpretation of perceptual quality rooted in the human visual system. Conventional approaches typically rely on fixed models to output scalar…

This paper presents a comprehensive pipeline for recognizing objects targeted by human pointing gestures using RGB images. As human-robot interaction moves toward more intuitive interfaces, the ability to identify targets of non-verbal…