Related papers: AlignVE: Visual Entailment Recognition Based on Al…
Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language…
Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality…
Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply…
Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images. Previous attempts typically tackle this problem using…
Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce…
We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic…
While vision-language models (VLMs) have made significant progress in multimodal perception (e.g., open-vocabulary object detection) with simple language queries, state-of-the-art VLMs still show limited ability to perceive complex queries…
Vision-language models (VLMs) enable open-ended visual question answering but remain prone to hallucinations. We present HEDGE, a unified framework for hallucination detection that combines controlled visual perturbations, semantic…
Referring image segmentation (RIS) aims to segment an object mentioned in natural language from an image. The main challenge is text-to-pixel fine-grained correlation. In the previous methods, the final results are obtained by convolutions…
Understanding relationships between objects is central to visual intelligence, with applications in embodied AI, assistive systems, and scene understanding. Yet, most visual relationship detection (VRD) models rely on a fixed predicate set,…
Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to…
The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are…
Visual relations, such as "person ride bike" and "bike next to car", offer a comprehensive scene understanding of an image, and have already shown their great utility in connecting computer vision and natural language. However, due to the…
Recognizing Textual Entailment (RTE) was proposed as a unified evaluation framework to compare semantic understanding of different NLP systems. In this survey paper, we provide an overview of different approaches for evaluating and…
Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings…
In this work, we propose a novel approach that predicts the relationships between various entities in an image in a weakly supervised manner by relying on image captions and object bounding box annotations as the sole source of supervision.…
Most existing research on visual question answering (VQA) is limited to information explicitly present in an image or a video. In this paper, we take visual understanding to a higher level where systems are challenged to answer questions…
Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still primarily assess language-based reasoning, often treating…
In this paper, we explore the potential of Vision-Language Models (VLMs), specifically CLIP, in predicting visual object relationships, which involves interpreting visual features from images into language-based relations. Current…
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a…