相关论文: CoReVAD: A Contextual Reasoning Framework for Trai…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significantly different conditions, such as atypical obstacles, its perceptual capabilities can…

We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in video temporal grounding: achieving temporally sensitive video-text alignment that remains robust to irrelevant background context.…

Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks. However, the multimodal reasoning capability has not been fully explored in existing models. In this paper, we propose a…

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…

Although deep neural networks (DNNs) enable great progress in video abnormal event detection (VAD), existing solutions typically suffer from two issues: (1) The localization of video events cannot be both precious and comprehensive. (2) The…

Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress,…

We present ConVOI, a novel method for autonomous robot navigation in real-world indoor and outdoor environments using Vision Language Models (VLMs). We employ VLMs in two ways: first, we leverage their zero-shot image classification…

The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While…

The growing demand for intelligent security in consumer electronics, such as smart home cameras and personal monitoring systems, is often hindered by the high computational cost and large model sizes of advanced AI. These limitations…

The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture.…

Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and…

We develop a novel framework for single-scene video anomaly localization that allows for human-understandable reasons for the decisions the system makes. We first learn general representations of objects and their motions (using deep…

Video Anomaly Detection (VAD), which aims to detect anomalies that deviate from expectation, has attracted increasing attention in recent years. Existing advancements in VAD primarily focus on model architectures and training strategies,…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This…

While reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs), its reliance on human-annotated labels leads to the scaling up dilemma, especially for complex tasks.…

Video anomaly detection (VAD) is an important computer vision problem. Thanks to the mode coverage capabilities of generative models, the likelihood-based paradigm is catching growing interest, as it can model normal distribution and detect…

Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data.…

Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are…