Related papers: Visual Recognition by Request
Object-aware reasoning in vision-language tasks poses significant challenges for current models, particularly in handling unseen objects, reducing hallucinations, and capturing fine-grained relationships in complex visual scenes. To address…
State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual…
While Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities for reasoning and self-correction at the textual level, these strengths provide minimal benefits for complex tasks centered on visual perception, such as…
Object detection and recognition are important problems in computer vision. Since these problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real-time, and dynamic object detection/recognition methods are…
This paper revisits visual representation in knowledge-based visual question answering (VQA) and demonstrates that using regional information in a better way can significantly improve the performance. While visual representation is…
Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then…
Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes, and spatial relations. They are increasingly deployed as a primary defense against automated…
It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and…
In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual…
Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Feature visualization…
Exploring and understanding efficient image representations is a long-standing challenge in computer vision. While deep learning has achieved remarkable progress across image understanding tasks, its internal representations are often…
Visual Relation Detection (VRD) aims to detect relationships between objects for image understanding. Most existing VRD methods rely on thousands of training samples of each relationship to achieve satisfactory performance. Some recent…
Visual Place Recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the…
A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to…
Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant…
Verifying a question's validity before answering is crucial in real-world applications, where users may provide imperfect instructions. In this scenario, an ideal model should address the discrepancies in the query and convey them to the…
Large vision and language models learned directly through image-text associations often lack detailed visual substantiation, whereas image segmentation tasks are treated separately from recognition, supervisedly learned without…
In an open-world setting, it is inevitable that an intelligent agent (e.g., a robot) will encounter visual objects, attributes or relationships it does not recognize. In this work, we develop an agent empowered with visual curiosity, i.e.…
We are interested in aligning how people think about objects and what machines perceive, meaning by this the fact that object recognition, as performed by a machine, should follow a process which resembles that followed by humans when…
While today's robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably see new objects in unconstrained settings, and thus will…