Search Results for author:
Found 44 papers, 21 papers with code
Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting
Temporal Knowledge Graph (TKG) forecasting is crucial for predicting future events using historical data.
Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph Reasoning
The results highlight the superiority of the n-ary subgraph reasoning framework and the exceptional inductive ability of NS-HART.
SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks.
Group Activity Recognition
Temporal Group Activity Localization
DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models
The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation.
Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted.
Demographic Attributes Prediction from Speech Using WavLM Embeddings
This paper introduces a general classifier based on WavLM features, to infer demographic characteristics, such as age, gender, native language, education, and country, from speech.
HAUR: Human Annotation Understanding and Recognition Through Text-Heavy Images
As part of this effort, we introduce the Human Annotation Understanding and Recognition-5 (HAUR-5) dataset, which encompasses five common types of human annotations.
Enhancing Facial Consistency in Conditional Video Generation via Facial Landmark Transformation
Existing methods often fail to maintain facial feature consistency due to mismatches between the facial landmarks extracted from source videos and the target facial features in the reference image.
X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation
Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlooking the inherent depth ambiguity issue.
Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning
Machine unlearning--enabling a trained model to forget specific data--is crucial for addressing biased data and adhering to privacy regulations like the General Data Protection Regulation (GDPR)'s "right to be forgotten".
ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs
Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs).
RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning
This approach effectively guides the model through complex multi-hop questions with chains of related facts.
Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding
Concurrently, the visual branch focuses on the selection of significant tokens, refining the attention mechanism to highlight the primary subject.
CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems
The results demonstrate that CL-DiffPhyCon achieves superior control performance with significant improvements in sampling efficiency.
Towards Scale-Aware Full Surround Monodepth with Transformers
Full surround monodepth (FSM) methods can learn from multiple camera views simultaneously in a self-supervised manner to predict the scale-aware depth, which is more practical for real-world applications in contrast to scale-ambiguous depth from a standalone monocular camera.
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
In the induction stage, the LLM is fed with few-shot normal reference samples and then summarizes these normal patterns to induce a set of rules for detecting anomalies.
Ranked #2 on
Video Anomaly Detection
on ShanghaiTech
TPIA: Towards Target-specific Prompt Injection Attack against Code-oriented Large Language Models
We show that our TPIA can successfully attack three representative open-source Code LLMs (with an attack success rate of up to 97. 9%) and two mainstream commercial Code LLM-integrated applications (with an attack success rate of over 90%) in all threat cases, using only a 12-token non-functional perturbation.
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters.
Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset
The method's effectiveness in improving language-video representation is evaluated through text-video retrieval using the MSR-VTT dataset and several multi-modal retrieval models.
Monocular Localization with Semantics Map for Autonomous Vehicles
To balance efficiency and accuracy, we propose a novel lightweight visual semantic localization algorithm that employs stable semantic features instead of low-level texture features.
SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years.
DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics
Structured data offers a sophisticated mechanism for the organization of information.
Robust Noisy Correspondence Learning with Equivariant Similarity Consistency
Accordingly we first calculate the ESC by comparing image and text semantic variations between a set of elaborated anchor points and other undivided training data.
Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision.
Ranked #5 on
Unsupervised 3D Human Pose Estimation
on Human3.6M
TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
Enhancing the domain generalization performance of Face Anti-Spoofing (FAS) techniques has emerged as a research focus.
Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning
In this study, we introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
Robustness-Guided Image Synthesis for Data-Free Quantization
Quantization has emerged as a promising direction for model compression.
CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
To generate high-quality segmentation predictions from referring expressions, we propose CLIPUNetr - a new CLIP-driven referring expression segmentation network.
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
Ranked #3 on
3D Semantic Segmentation
on SemanticKITTI
(using extra training data)
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods.
Ranked #1 on
3D Multi-Object Tracking
on Waymo Open Dataset
SneakyPrompt: Jailbreaking Text-to-image Generative Models
Text-to-image generative models such as Stable Diffusion and DALL$\cdot$E raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones.
SGL: Structure Guidance Learning for Camera Localization
Camera localization is a classical computer vision task that serves various Artificial Intelligence and Robotics applications.
LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
Notably, LoGoNet ranks 1st on Waymo 3D object detection leaderboard and obtains 81. 02 mAPH (L2) detection performance.
HGV4Risk: Hierarchical Global View-guided Sequence Representation Learning for Risk Prediction
Moreover, the hierarchical representations at both instance level and channel level can be coordinated by the heterogeneous information aggregation under the guidance of global view.
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Federated learning (FL) allows multiple clients to collaboratively train a deep learning model.
A Real-Time Fusion Framework for Long-term Visual Localization
In this paper, we present an efficient client-server visual localization architecture that fuses global and local pose estimations to realize promising precision and efficiency.
Multi-modal Graph Learning for Disease Prediction
For disease prediction tasks, most existing graph-based methods tend to define the graph manually based on specified modality (e. g., demographic information), and then integrated other modalities to obtain the patient representation by Graph Representation Learning (GRL).
FCNet: A Convolutional Neural Network for Arbitrary-Length Exposure Estimation
For image exposure enhancement, the tasks of Single-Exposure Correction (SEC) and Multi-Exposure Fusion (MEF) are widely studied in the image processing community.
Pose Refinement with Joint Optimization of Visual Points and Lines
High-precision camera re-localization technology in a pre-established 3D environment map is the basis for many tasks, such as Augmented Reality, Robotics and Autonomous Driving.
Retrieval and Localization with Observation Constraints
The localization pipeline is designed as a coarse-to-fine paradigm.
Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing
For the vehicle detection and tracking module, we adopted YOLOv5 and multi-scale tracking to localize the anomalies.
Practical Blind Membership Inference Attack via Differential Comparisons
The success of the former heavily depends on the quality of the shadow model, i. e., the transferability between the shadow and the target; the latter, given only blackbox probing access to the target model, cannot make an effective inference of unknowns, compared with MI attacks using shadow models, due to the insufficient number of qualified samples labeled with ground truth membership information.
Big-Data Clustering: K-Means or K-Indicators?
The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some "feature spaces", as is in spectral clustering.
Efficient Traffic-Sign Recognition with Scale-aware CNN
The paper presents a Traffic Sign Recognition (TSR) system, which can fast and accurately recognize traffic signs of different sizes in images.
