Search Results for author:
Found 22 papers, 10 papers with code
Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities
The first stage, AI for Network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences.
Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly
Specifically, each instance of our ECVA involves three sets of human annotations to indicate "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality.
MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization
At the training stage, we tune our proposed MalT5, a novel LLM-based code model, on the MalS and benign pseudocode datasets.
ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions
The main challenges lie in aligning key contextual cues in two modalities, where these subtle cues are concealed in tiny areas of multiple contrastive images and within the complex linguistics of textual descriptions.
Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
In pursuit of these answers, we present a comprehensive benchmark for Causation Understanding of Video Anomaly (CUVA).
Can We Improve Channel Reciprocity via Loop-back Compensation for RIS-assisted Physical Layer Key Generation
The results demonstrate a significant improvement in both the rate of key generation assisted by the RIS and the consistency of the generated keys, showing great potential for the practical deployment of our LoCKey in future wireless systems.
Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
In addition we also introduce MMEval a novel evaluation metric designed to better align with human preferences for CUVA facilitating the measurement of existing LLMs in comprehending the underlying cause and corresponding effect of video anomalies.
Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks
This finding motivates us to present a novel method that aims to harden GCNs by automatically learning Latent Homophilic Structures over heterophilic graphs.
Ranked #5 on
Node Classification
on Actor
DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding
Multimodal Sarcasm Understanding (MSU) has a wide range of applications in the news field such as public opinion analysis and forgery detection.
Passive Eavesdropping Can Significantly Slow Down RIS-Assisted Secret Key Generation
Reconfigurable Intelligent Surface (RIS) assisted physical layer key generation has shown great potential to secure wireless communications by smartly controlling signals such as phase and amplitude.
Disentangled Dynamic Intrusion Detection
Specifically, the proposed DIDS first disentangles traffic features by a non-parameterized optimization, automatically differentiating tens and hundreds of complex features of various attacks.
Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications
We argue that central to the success of ESC is the robust interpretation of conveyed semantics at the receiver side, especially for security-critical applications such as automatic driving and smart healthcare.
Boosting Physical Layer Black-Box Attacks with Semantic Adversaries in Semantic Communications
To this end, we present SemBLK, a novel method that can learn to generate destructive physical layer semantic attacks for an ESC system under the black-box setting, where the adversaries are imperceptible to humans.
You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding.
Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition
Automatic emotion recognition (AER) based on enriched multimodal inputs, including text, speech, and visual clues, is crucial in the development of emotionally intelligent machines.
Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction
Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues.
Uncovering Main Causalities for Long-tailed Information Extraction
Information Extraction (IE) aims to extract structural information from unstructured texts.
Interventional Video Grounding with Dual Contrastive Learning
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
Video Corpus Moment Retrieval with Contrastive Learning
We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR.
Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities.
Counterfactual Thinking for Long-tailed Information Extraction
However, in practice, the long-tailed and imbalanced data may lead to severe bias issues for deep learning models, due to very few training instances available for the tail classes.
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities.
Ranked #9 on
Relation Extraction
on GDA
