相关论文: Multiscale Video Transformers for Class Agnostic S…

We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…

Autonomous driving is a challenging topic that requires complex solutions in perception tasks such as recognition of road, lanes, traffic signs or lights, vehicles and pedestrians. Through years of research, computer vision has grown…

Temporally consistent dense video annotations are scarce and hard to collect. In contrast, image segmentation datasets (and pre-trained models) are ubiquitous, and easier to label for any novel task. In this paper, we introduce a method to…

Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and…

While large-scale diffusion models have revolutionized video synthesis, achieving precise control over both multi-subject identity and multi-granularity motion remains a significant challenge. Recent attempts to bridge this gap often suffer…

The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we…

Current state-of-the-art object detection and segmentation methods work well under the closed-world assumption. This closed-world setting assumes that the list of object categories is available during training and deployment. However, many…

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…

We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to…

Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most existing approaches…

Object detection in videos plays a crucial role in advancing applications such as public safety and anomaly detection. Existing methods have explored different techniques, including CNN, deep learning, and Transformers, for object detection…

Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on…

Safety and decline of road traffic accidents remain important issues of autonomous driving. Statistics show that unintended lane departure is a leading cause of worldwide motor vehicle collisions, making lane detection the most promising…

Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without…

Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have…

Convolutional networks reach top quality in pixel-level video object segmentation but require a large amount of training data (1k~100k) to deliver such results. We propose a new training strategy which achieves state-of-the-art results…

Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment…

While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is…

Critical research about camera-and-LiDAR-based semantic object segmentation for autonomous driving significantly benefited from the recent development of deep learning. Specifically, the vision transformer is the novel ground-breaker that…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…