Related papers: Object-to-Scene: Learning to Transfer Object Knowl…

Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…

Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities. This paper presents a novel approach which exploits rich mid-level convolutional…

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and…

Spatial relationships between objects provide important information for text-based image retrieval. As users are more likely to describe a scene from a real world perspective, using 3D spatial relationships rather than 2D relationships that…

General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which…

Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and…

We present the Object-Based Sub-Environment Recognition (OBSER) framework, a novel Bayesian framework that infers three fundamental relationships between sub-environments and their constituent objects. In the OBSER framework, metric and…

Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them.…

While general object recognition is still far from being solved, this paper proposes a way for a robot to recognize every object at an almost human-level accuracy. Our key observation is that many robots will stay in a relatively closed…

Deep neural networks have become the primary learning technique for object recognition. Videos, unlike still images, are temporally coherent which makes the application of deep networks non-trivial. Here, we investigate how motion can aid…

Self-supervised Object Segmentation (SOS) aims to segment objects without any annotations. Under conditions of multi-camera inputs, the structural, textural and geometrical consistency among each view can be leveraged to achieve…

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their…

Localization is an essential technique in mobile robotics. In a complex environment, it is necessary to fuse different localization modules to obtain more robust results, in which the error model plays a paramount role. However,…

Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…

We propose an end-to-end learning framework for segmenting generic objects in both images and videos. Given a novel image or video, our approach produces a pixel-level mask for all "object-like" regions---even for object categories never…

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are…

Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…

Visual relocalization aims to estimate the pose of a camera from one or more images. In recent years deep learning based pose regression methods have attracted many attentions. They feature predicting the absolute poses without relying on…

Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and scene understanding has remained elusive due to the high…

Tactile perception is crucial for embodied intelligent robots to recognize objects. Vision-based tactile sensors extract object physical attributes multidimensionally using high spatial resolution; however, this process generates abundant…