Related papers: OED: Towards One-stage End-to-End Dynamic Scene Gr…
Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. Since datasets in this domain are often gathered from limited video scenes, models tend to…
We present a unified representation for actionable spatial perception: 3D Dynamic Scene Graphs. Scene graphs are directed graphs where nodes represent entities in the scene (e.g. objects, walls, rooms), and edges represent relations (e.g.…
Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph. Existing SGG approaches generally not only…
This paper proposes a novel edge computing enabled real-time video analysis system for intelligent visual devices. The proposed system consists of a tracking-assisted object detection module (TAODM) and a region of interesting module…
Current open-vocabulary scene graph generation algorithms highly rely on both 3D scene point cloud data and posed RGB-D images and thus have limited applications in scenarios where RGB-D images or camera poses are not readily available. To…
It has long been challenging to recover the underlying dynamic 3D scene representations from a monocular RGB video. Existing works formulate this problem into finding a single most plausible solution by adding various constraints such as…
Accurate traffic prediction is a challenging task in intelligent transportation systems because of the complex spatio-temporal dependencies in transportation networks. Many existing works utilize sophisticated temporal modeling approaches…
In panoptic scene graph generation (PSGG), models retrieve interactions between objects in an image which are grounded by panoptic segmentation masks. Previous evaluations on panoptic scene graphs have been subject to an erroneous…
Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects…
Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated…
Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous…
Inspired by the activity-silent and persistent activity mechanisms in human visual perception biology, we design a Unified Static and Dynamic Network (UniSDNet), to learn the semantic association between the video and text/audio queries in…
Reconstruction dynamic visual scenes from electroencephalography (EEG) signals remains a primary challenge in brain decoding, limited by the low spatial resolution of EEG, a temporal mismatch between neural recordings and video dynamics,…
Recently, one-stage detectors have achieved competitive accuracy and faster speed compared with traditional two-stage detectors on image data. However, in the field of video object detection (VOD), most existing VOD methods are still based…
Video Scene Graph Generation (VidSGG) aims to capture dynamic relationships among entities by sequentially analyzing video frames and integrating visual and semantic information. However, VidSGG is challenged by significant biases that skew…
The latest emerged 4D Panoptic Scene Graph (4D-PSG) provides an advanced-ever representation for comprehensively modeling the dynamic 4D visual real world. Unfortunately, current pioneering 4D-PSG research can primarily suffer from data…
This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously. Most of the scene graph generation frameworks use a pre-trained two-stage object detector, like Faster R-CNN,…
Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedestrians and temporal dependencies of individuals. They…
3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations…
Directly producing planning results from raw sensors has been a long-desired solution for autonomous driving and has attracted increasing attention recently. Most existing end-to-end autonomous driving methods factorize this problem into…