相关论文: Winning the ICCV'2021 VALUE Challenge: Task-aware …

In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer…

Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective…

Visual Question Answering (VQA) has recently emerged as a potential research domain, captivating the interest of many in the field of artificial intelligence and computer vision. Despite the prevalence of approaches in English, there is a…

Visual Question Answering (VQA) requires AI models to comprehend data in two domains, vision and text. Current state-of-the-art models use learned attention mechanisms to extract relevant information from the input domains to answer a…

Visual reasoning, the capability to interpret visual input in response to implicit text query through multi-step reasoning, remains a challenge for deep learning models due to the lack of relevant benchmarks. Previous work in visual…

We propose a multiple instance learning approach to content-based retrieval of classroom video for the purpose of supporting human assessing the learning environment. The key element of our approach is a mapping between the semantic…

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…

Visual commonsense understanding requires Vision Language (VL) models to not only understand image and text but also cross-reference in-between to fully integrate and achieve comprehension of the visual scene described. Recently, various…

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for…

The advent and proliferation of large multi-modal models (LMMs) have introduced new paradigms to computer vision, transforming various tasks into a unified visual question answering framework. Video Quality Assessment (VQA), a classic field…

Accurate visual understanding is imperative for advancing autonomous systems and intelligent robots. Despite the powerful capabilities of vision-language models (VLMs) in processing complex visual scenes, precisely recognizing obscured or…

This paper proposes CQ-VQA, a novel 2-level hierarchical but end-to-end model to solve the task of visual question answering (VQA). The first level of CQ-VQA, referred to as question categorizer (QC), classifies questions to reduce the…

As language and visual understanding by machines progresses rapidly, we are observing an increasing interest in holistic architectures that tightly interlink both modalities in a joint learning and inference process. This trend has allowed…

We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn…

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…

Recent advances in text-to-video (T2V) technology, as demonstrated by models such as Runway Gen-3, Pika, Sora, and Kling, have significantly broadened the applicability and popularity of the technology. This progress has created a growing…

Vision-Language Models (VLMs) have achieved strong performance on standard vision-language benchmarks, yet often rely on surface-level recognition rather than deeper reasoning. We propose visual word puzzles as a challenging alternative, as…

We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary…

Semantic segmentation research has recently witnessed rapid progress, but many leading methods are unable to identify object instances. In this paper, we present Multi-task Network Cascades for instance-aware semantic segmentation. Our…

Reranking is a critical component of modern retrieval systems, which typically pair an efficient first-stage retriever with a more expressive model to refine results. While large reasoning models have driven rapid progress in text-centric…