Related papers: A Tactical Behaviour Recognition Framework Based o…
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 dialogue emotion recognition captures emotional cues by fusing text, visual, and audio modalities. However, existing approaches still suffer from notable limitations in modeling emotional dependencies and learning multimodal…
Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps. However, current methods have difficulty in effectively combining features from both temporal and spatial graph dimensions…
Although Graph Neural Networks (GNNs) have shown promise for smart contract vulnerability detection, they still face significant limitations. Homogeneous graph models fail to capture the interplay between control flow and data dependencies,…
Many large-scale applications can be elegantly represented using graph structures. Their scalability, however, is often limited by the domain knowledge required to apply them. To address this problem, we propose a novel Causal Temporal…
Relational thinking refers to the inherent ability of humans to form mental impressions about relations between sensory signals and prior knowledge, and subsequently incorporate them into their model of their world. Despite the crucial role…
Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to…
Resource allocation in tactical ad-hoc networks presents unique challenges due to their dynamic and multi-hop nature. Accurate prediction of future network connectivity is essential for effective resource allocation in such environments. In…
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard benchmarks, we are…
Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak…
Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information.…
Situational Graphs (S-Graphs) merge geometric models of the environment generated by Simultaneous Localization and Mapping (SLAM) approaches with 3D scene graphs into a multi-layered jointly optimizable factor graph. As an advantage,…
Graph convolutional networks (GCNs) can effectively capture the features of related nodes and improve the performance of the model. More attention is paid to employing GCN in Skeleton-Based action recognition. But existing methods based on…
We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a…
Nuanced understanding and the generation of detailed descriptive content for (bimanual) manipulation actions in videos is important for disciplines such as robotics, human-computer interaction, and video content analysis. This study…
We address the problem of text-guided video temporal grounding, which aims to identify the time interval of a certain event based on a natural language description. Different from most existing methods that only consider RGB images as…
Replay attacks remain a critical vulnerability for automatic speaker verification systems, particularly in real-time voice assistant applications. In this work, we propose acoustic maps as a novel spatial feature representation for replay…
Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture this rich visual and semantic context, we propose using two…
Constraint-based methods and noise-based methods are two distinct families of methods proposed for uncovering causal graphs from observational data. However, both operate under strong assumptions that may be challenging to validate or could…
Audio-visual video parsing (AVVP) aims to detect event categories and their temporal boundaries in videos, typically under weak supervision. Existing methods mainly focus on (i) improving temporal modeling using attention-based…