Related papers: VREN: Volleyball Rally Dataset with Expression Not…
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the…
Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task. In reality, a truly useful VidL system is expected to be easily generalizable to diverse tasks, domains, and datasets. To…
Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential…
Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. However, their potential to comprehend embodied environments and navigate within them remains…
Machine Reading Comprehension (MRC) is a challenging Natural Language Processing(NLP) research field with wide real-world applications. The great progress of this field in recent years is mainly due to the emergence of large-scale datasets…
We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first to provide large-scale, fine-grained annotations for racket…
Video Referring Expression Comprehension (REC) aims to localize a target object in video frames referred by the natural language expression. Recently, the Transformerbased methods have greatly boosted the performance limit. However, we…
Humans effortlessly "program" one another by communicating goals and desires in natural language. In contrast, humans program robotic behaviours by indicating desired object locations and poses to be achieved, by providing RGB images of…
We present a novel human annotated dataset for evaluating the ability for visual-language models to generate both short and long descriptions for real-world video clips, termed DeVAn (Dense Video Annotation). The dataset contains 8.5K…
Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently challenging due to the requirement of known ground-truth causal…
The increasing demand for high-quality, diverse training data poses a significant bottleneck in advancing vision-language models (VLMs). This paper presents VLM Dialog Games, a novel and scalable self-improvement framework for VLMs. Our…
We introduce AirLetters, a new video dataset consisting of real-world videos of human-generated, articulated motions. Specifically, our dataset requires a vision model to predict letters that humans draw in the air. Unlike existing video…
Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely limited by the lack of robust evaluation benchmarks and high-quality preference data. To…
Modern reinforcement learning (RL) struggles to capture real-world cause-and-effect dynamics, leading to inefficient exploration due to extensive trial-and-error actions. While recent efforts to improve agent exploration have leveraged…
Vision-Language Translation (VLT) is a challenging task that requires accurately recognizing multilingual text embedded in images and translating it into the target language with the support of visual context. While recent Large…
One of the requirements for team sports analysis is to track and recognize players. Many tracking and reidentification methods have been proposed in the context of video surveillance. They show very convincing results when tested on public…
Vision-and-language navigation (VLN) aims to develop agents capable of navigating in realistic environments. While recent cross-modal training approaches have significantly improved navigation performance in both indoor and outdoor…
Event Detection (ED) is an important task in natural language processing. In the past few years, many datasets have been introduced for advancing ED machine learning models. However, most of these datasets are under-explored because not…
In AI-facilitated teaching, leveraging various query styles to interpret abstract text descriptions is crucial for ensuring high-quality teaching. However, current retrieval models primarily focus on natural text-image retrieval, making…
Recent advances in Vision Language Models (VLMs) have driven significant progress in visual reasoning. However, open-source VLMs still lag behind proprietary systems, largely due to the lack of high-quality reasoning data. Existing datasets…