相关论文: CCTVBench: Contrastive Consistency Traffic VideoQA…

Supervised learning, while prevalent for information cascade modeling, often requires abundant labeled data in training, and the trained model is not easy to generalize across tasks and datasets. It often learns task-specific…

Adaptive traffic signal control (TSC) has demonstrated strong effectiveness in managing dynamic traffic flows. However, conventional methods often struggle when unforeseen traffic incidents occur (e.g., accidents and road maintenance),…

We introduce CompareBench, a benchmark for evaluating visual comparison reasoning in vision-language models (VLMs), a fundamental yet understudied skill. CompareBench consists of 1000 QA pairs across four tasks: quantity (600), temporal…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

Traffic monitoring is crucial for urban mobility, road safety, and intelligent transportation systems (ITS). Deep learning has advanced video-based traffic monitoring through video question answering (VideoQA) models, enabling structured…

Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness. Such models typically…

Traffic video description and analysis have received much attention recently due to the growing demand for efficient and reliable urban surveillance systems. Most existing methods only focus on locating traffic event segments, which…

Multimodal large language models (MLLMs) have recently achieved remarkable progress in radiology by integrating visual perception with natural language understanding. However, they often generate clinically unsupported descriptions, known…

Achieving both efficiency and strong discriminative ability in lightweight visual tracking is a challenge, especially on mobile and edge devices with limited computational resources. Conventional lightweight trackers often struggle with…

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…

Despite the significant advancements of Large Vision-Language Models (LVLMs) on established benchmarks, there remains a notable gap in suitable evaluation regarding their applicability in the emerging domain of long-context streaming video…

Despite Visual Question Answering (VQA) has realized impressive progress over the last few years, today's VQA models tend to capture superficial linguistic correlations in the train set and fail to generalize to the test set with different…

Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese malicious queries typically conceal intent via homophones,…

Traffic Management Centers (TMCs) routinely use traffic cameras to provide situational awareness regarding traffic, road, and weather conditions. Camera footage is quite useful for a variety of diagnostic purposes; yet, most footage is kept…

Investigating hallucination issues in large language models (LLMs) within cross-lingual and cross-modal scenarios can greatly advance the large-scale deployment in real-world applications. Nevertheless, the current studies are limited to a…

Multimodal Large Language Models (MLLMs) have shown impressive perception and reasoning capabilities, yet they often suffer from hallucinations -- generating outputs that are linguistically coherent but inconsistent with the context of the…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

In this paper, we propose a Disentangled Counterfactual Learning~(DCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects' physics commonsense based on both video and audio input, with the main challenge…

Recent advances in open-vocabulary object detection focus primarily on two aspects: scaling up datasets and leveraging contrastive learning to align language and vision modalities. However, these approaches often neglect internal…

The widespread adoption of dashcams has made video evidence in traffic accidents increasingly abundant, yet transforming "what happened in the video" into "who is responsible under which legal provisions" still relies heavily on human…