Related papers: Perception Test 2025: Challenge Summary and a Unif…

Depth-aware video panoptic segmentation is a promising approach to camera based scene understanding. However, the current state-of-the-art methods require costly video annotations and use a complex training pipeline compared to their…

Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB challenge, this paper…

This paper introduces MCTrack, a new 3D multi-object tracking method that achieves state-of-the-art (SOTA) performance across KITTI, nuScenes, and Waymo datasets. Addressing the gap in existing tracking paradigms, which often perform well…

Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table recognition (TR) has mainly centered around complex task-specific combinations of…

Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment.…

TextVQA requires models to read and reason about text in images to answer questions about them. Specifically, models need to incorporate a new modality of text present in the images and reason over it to answer TextVQA questions. In this…

In recent years, 3D object perception has become a crucial component in the development of autonomous driving systems, providing essential environmental awareness. However, as perception tasks in autonomous driving evolve, their variants…

The major challenge in audio-visual event localization task lies in how to fuse information from multiple modalities effectively. Recent works have shown that attention mechanism is beneficial to the fusion process. In this paper, we…

Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts.…

Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess the cognitive capabilities required for high-level tasks,…

Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings…

In this paper, we propose a simple yet unified single object tracking (SOT) framework, dubbed SUTrack. It consolidates five SOT tasks (RGB-based, RGB-Depth, RGB-Thermal, RGB-Event, RGB-Language Tracking) into a unified model trained in a…

Although recent efforts in image quality assessment (IQA) have achieved promising performance, there still exists a considerable gap compared to the human visual system (HVS). One significant disparity lies in humans' seamless transition…

Open-world video recognition is challenging since traditional networks are not generalized well on complex environment variations. Alternatively, foundation models with rich knowledge have recently shown their generalization power. However,…

Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes. In this paper, we introduce the 6th Large-scale Video Object Segmentation (LSVOS) challenge in…

Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person…

Human perception of similarity across uni- and multimodal inputs is highly complex, making it challenging to develop automated metrics that accurately mimic it. General purpose vision-language models, such as CLIP and large multi-modal…

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…

While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic…

Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video…