相关论文: From Web to Pixels: Bringing Agentic Search into V…

Visual search is an essential part of almost any everyday human goal-directed interaction with the environment. Nowadays, several algorithms are able to predict gaze positions during simple observation, but few models attempt to simulate…

Using mathematical modeling and human subjects experiments, this research explores the extent to which emerging webcams might leak recognizable textual and graphical information gleaming from eyeglass reflections captured by webcams. The…

Vision-Language Models (VLMs) frequently misread values, hallucinate details, and confuse overlapping elements in charts. Current approaches rely solely on pixel interpretation, creating a Pixel-Only Bottleneck: agents treat interactive…

Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While…

Distinguishing target from non-target fixations during visual search is a fundamental building block to understand users' intended actions and to build effective assistance systems. While prior research indicated the feasibility of…

This paper investigates the problem of modeling Internet images and associated text or tags for tasks such as image-to-image search, tag-to-image search, and image-to-tag search (image annotation). We start with canonical correlation…

We propose Perceptual Taxonomy, a structured process of scene understanding that first recognizes objects and their spatial configurations, then infers task-relevant properties such as material, affordance, function, and physical attributes…

We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…

Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as…

Existing benchmarks for multimodal agentic search evaluate multimodal search and visual browsing, but visual evidence is either confined to the input or treated as an answer endpoint rather than part of an interleaved search trajectory. We…

Estimating eye-gaze from images alone is a challenging task, in large parts due to un-observable person-specific factors. Achieving high accuracy typically requires labeled data from test users which may not be attainable in real…

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Gaze and face tracking algorithms have traditionally battled a compromise between computational complexity and accuracy; the most accurate neural net algorithms cannot be implemented in real time, but less complex real-time algorithms…

In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative…

Deep research agents integrate fragmented evidence through multi-step tool use. BrowseComp offers a text-only testbed for such agents, but existing multimodal benchmarks rarely require both weak visual cues composition and BrowseComp-style…

The human brain is adept at solving difficult high-level visual processing problems such as image interpretation and object recognition in natural scenes. Over the past few years neuroscientists have made remarkable progress in…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different…

Camera-based autonomous systems that emulate human perception are increasingly being integrated into safety-critical platforms. Consequently, an established body of literature has emerged that explores adversarial attacks targeting the…

Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Expansion (open-web search). However, existing evaluations fall…