Related papers: Learning Scene Context Without Images

Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this…

Semantic 3D scene understanding is a problem of critical importance in robotics. While significant advances have been made in simultaneous localization and mapping algorithms, robots are still far from having the common sense knowledge…

Computer vision systems currently lack the ability to reliably recognize artistically rendered objects, especially when such data is limited. In this paper, we propose a method for recognizing objects in artistic modalities (such as…

Autonomous driving has achieved rapid development over the last few decades, including the machine perception as an important issue of it. Although object detection based on conventional cameras has achieved remarkable results in 2D/3D,…

While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems…

Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection…

This paper describes a method of estimating the traversability of plant parts covering a path and navigating through them for mobile robots operating in plant-rich environments. Conventional mobile robots rely on scene recognition methods…

Visual domain gaps often impact object detection performance. Image-to-image translation can mitigate this effect, where contrastive approaches enable learning of the image-to-image mapping under unsupervised regimes. However, existing…

The pursuit of high performance on public benchmarks has been the driving force for research in scene text recognition, and notable progress has been achieved. However, a close investigation reveals a startling fact that the…

Understanding a visual scene incorporates objects, relationships, and context. Traditional methods working on an image mostly focus on object detection and fail to capture the relationship between the objects. Relationships can give rich…

Object detection is a critical field in computer vision focusing on accurately identifying and locating specific objects in images or videos. Traditional methods for object detection rely on large labeled training datasets for each object…

This paper focuses on vision-based pose estimation for multiple rigid objects placed in clutter, especially in cases involving occlusions and objects resting on each other. Progress has been achieved recently in object recognition given…

A robot operating in a household makes observations of multiple objects as it moves around over the course of days or weeks. The objects may be moved by inhabitants, but not completely at random. The robot may be called upon later to…

With the proliferation of imaging sensors, the volume of multi-modal imagery far exceeds the ability of human analysts to adequately consume and exploit it. Full motion video (FMV) possesses the extra challenge of containing large amounts…

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization…

Our daily life is surrounded by textual information. Nowadays, the automatic collection of textual information becomes possible owing to the drastic improvement of scene text detectors and recognizer. The purpose of this paper is to conduct…

Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…