Related papers: EEA: Exploration-Exploitation Agent for Long Video…
Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus…
Document-level Event Argument Extraction (EAE) faces two challenges due to increased input length: 1) difficulty in distinguishing semantic boundaries between events, and 2) interference from redundant information. To address these issues,…
Integrating higher level visual and linguistic interpretations is at the heart of human intelligence. As automatic visual category recognition in images is approaching human performance, the high level understanding in the dynamic…
Entity alignment (EA) aims to identify entities referring to the same real-world object across different knowledge graphs (KGs). Recent approaches based on large language models (LLMs) typically obtain entity embeddings through knowledge…
Finite Element Analysis (FEA) is a powerful but computationally intensive method for simulating physical phenomena. Recent advancements in machine learning have led to surrogate models capable of accelerating FEA. Yet there are still…
Despite decades of work, surveillance still struggles to find specific targets across long, multi-camera video. Prior methods -- tracking pipelines, CLIP based models, and VideoRAG -- require heavy manual filtering, capture only shallow…
Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical,…
With the increase in scale and availability of digital text generated on the web, enterprises such as online retailers and aggregators often use text analytics to mine and analyze the data to improve their services and products alike. Text…
Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has…
Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in…
With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large vision language models (LVLMs) have enhanced…
Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods…
Efficiently understanding long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding and address a fundamental issue pertaining to all…
Entity alignment (EA) aims to find the equivalent entity pairs between different knowledge graphs (KGs), which is crucial to promote knowledge fusion. With the wide use of temporal knowledge graphs (TKGs), time-aware EA (TEA) methods appear…
Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual…
Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon execution, tight…
Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency during autoregressive generation. Speculative Decoding (SD) mitigates this by applying a draft-and-verify paradigm, yet existing…
Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process videos largely in a single-pass manner with limited support…
Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a…
Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as…