Related papers: Constructing Holistic Spatio-Temporal Scene Graph …
Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with…
Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video. However, due to the long-tailed training data in datasets, the…
Graph based representation has been widely used in modelling spatio-temporal relationships in video understanding. Although effective, existing graph-based approaches focus on capturing the human-object relationships while ignoring…
Dynamic scene understanding is the ability of a computer system to interpret and make sense of the visual information present in a video of a real-world scene. In this thesis, we present a series of frameworks for dynamic scene…
Multimodal LLMs have advanced vision-language tasks but still struggle with understanding video scenes. To bridge this gap, Video Scene Graph Generation (VidSGG) has emerged to capture multi-object relationships across video frames.…
We propose a new framework for understanding and representing related salient events in a video using visual semantic role labeling. We represent videos as a set of related events, wherein each event consists of a verb and multiple entities…
As a natural extension of the image synthesis task, video synthesis has attracted a lot of interest recently. Many image synthesis works utilize class labels or text as guidance. However, neither labels nor text can provide explicit…
Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep…
Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…
Reasoning about complex visual scenes involves perception of entities and their relations. Scene graphs provide a natural representation for reasoning tasks, by assigning labels to both entities (nodes) and relations (edges). Unfortunately,…
Dynamic scene graph generation extends scene graph generation from images to videos by modeling entity relationships and their temporal evolution. However, existing methods either generate scene graphs from observed frames without…
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual…
This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new {\em detect-to-track} paradigm for this task by…
Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into semantic triplets <Subject-Predicate-Object> for accurate…
Temporal sentence localization in videos (TSLV) aims to retrieve the most interested segment in an untrimmed video according to a given sentence query. However, almost of existing TSLV approaches suffer from the same limitations: (1) They…
Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical vision features, thus inevitably falling prey to the problem…
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…
Spatio-Temporal Scene Graphs (STSGs) provide a concise and expressive representation of dynamic scenes by modeling objects and their evolving relationships over time. However, real-world visual relationships often exhibit a long-tailed…
Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes. This paper addresses two key challenges: (1) conventional…
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…