相关论文: TrUMAn: Trope Understanding in Movies and Animatio…

The human ability of deep cognitive skills are crucial for the development of various real-world applications that process diverse and abundant user generated input. While recent progress of deep learning and natural language processing…

Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet…

Most existing robotic datasets capture static scene data and thus are limited in evaluating robots' dynamic performance. To address this, we present a mobile robot oriented large-scale indoor dataset, denoted as THUD (Tsinghua University…

As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by…

The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segmentation masks by…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, despite being a critical real-world modality, remains relatively underexplored in…

While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual…

Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like…

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species. In this paper, we introduce an effective and interpretable network module, the…

Video reasoning, the task of enabling machines to infer from dynamic visual content through multi-step logic, is crucial for advanced AI. While the Chain-of-Thought (CoT) mechanism has enhanced reasoning in text-based tasks, its application…

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a…

Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data already, less work has been done with sounds. This work develops an approach for scene…

Humans naturally understand moments in a video by integrating visual and auditory cues. For example, localizing a scene in the video like "A scientist passionately speaks on wildlife conservation as dramatic orchestral music plays, with the…

Human intelligence requires correctness and robustness, with the former being foundational for the latter. In video understanding, correctness ensures the accurate interpretation of visual content, and robustness maintains consistent…

Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…

Computer-use agents can operate computers and automate laborious tasks, but despite recent rapid progress, they still lag behind human users, especially when tasks require domain-specific procedural knowledge about particular applications,…

Causality knowledge is vital to building robust AI systems. Deep learning models often perform poorly on tasks that require causal reasoning, which is often derived using some form of commonsense knowledge not immediately available in the…

Our brains extract durable, generalizable knowledge from transient experiences of the world. Artificial neural networks come nowhere close to this ability. When tasked with learning to classify objects by training on non-repeating video…

While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required…

Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…