相关论文: The Third Place Solution for CVPR2022 AVA Accessib…

We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features…

Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS). In this technical report, we investigated and validated the effectiveness of…

Visual Question Answering (VQA) is an increasingly popular topic in deep learning research, requiring coordination of natural language processing and computer vision modules into a single architecture. We build upon the model which placed…

We present a new video understanding pentathlon challenge, an open competition held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020. The objective of the challenge was to explore and evaluate…

The increasing shortage of drivers poses a significant threat to vulnerable populations, particularly seniors and disabled individuals who heavily depend on public transportation for accessing healthcare services and social events.…

Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this…

This study proposed a new methodological approach for the assessment of automated vehicle acceptance (AVA) from the perspective of road users inside and outside of AVs pre- and post- AV experience. Users can be drivers and passengers, but…

Multi-goal reaching is an important problem in reinforcement learning needed to achieve algorithmic generalization. Despite recent advances in this field, current algorithms suffer from three major challenges: high sample complexity,…

One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods such as SRAL and multi-process fusion. These approaches come…

Recent studies show that the visual place recognition (VPR) method using pre-trained visual foundation models can achieve promising performance. In our previous work, we propose a novel method to realize seamless adaptation of foundation…

In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples. To address this, we consider the problem of training models in a risk-averse manner. We propose…

Visual Place Recognition (VPR) is a fundamental yet challenging task for small Unmanned Aerial Vehicle (UAV). The core reasons are the extreme viewpoint changes, and limited computational power onboard a UAV which restricts the…

This technical report presents the 2nd winning model for AQTC, a task newly introduced in CVPR 2022 LOng-form VidEo Understanding (LOVEU) challenges. This challenge faces difficulties with multi-step answers, multi-modal, and diverse and…

The VAST Challenges have been shown to be an effective tool in visual analytics education, encouraging student learning while enforcing good visualization design and development practices. However, research has observed that students often…

People with visual impairments face numerous challenges in their daily lives, including mobility, access to information, independent living, and employment. Artificial Intelligence (AI) with Computer Vision (CV) has the potential to improve…

When academic researchers develop and validate autonomous driving algorithms, there is a challenge in balancing high-performance capabilities with the cost and complexity of the vehicle platform. Much of today's research on autonomous…

Real-world vision-language applications demand varying levels of perceptual granularity. However, most existing visual large language models (VLLMs), such as LLaVA, pre-assume a fixed resolution for downstream tasks, which leads to subpar…

In this paper, we present the runner-up solution for the Ego4D EgoSchema Challenge at CVPR 2025 (Confirmed on May 20, 2025). Inspired by the success of large models, we evaluate and leverage leading accessible multimodal large models and…

Automated vehicle acceptance (AVA) has been measured mostly subjectively by questionnaires and interviews, with a main focus on drivers inside automated vehicles (AVs). To ensure that AVs are widely accepted by the public, ensuring the…

Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations independently at each timestep. This history-agnostic design treats robot manipulation as a Markov…