Search Results for author:
Found 78 papers, 39 papers with code
Pixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference & Application
Inference & Application","We formalize concepts around geometric occlusion in 2D images (i. e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation.
Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
FLBuff is inspired by our insight that non-iids can be modeled as omni-directional expansion in representation space while backdoor attacks as uni-directional.
Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks
Our comprehensive evaluations show that GeminiGuard consistently outperforms SOTA defenses under various settings.
Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing
We believe our approach paves the way for a more precise understanding of brain signals in the future.
RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization
3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique.
Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shifts
Our model posits that label noise arises from a stochastic shift in the latent variable, providing a more robust and beneficial means for noisy learning.
LIMO: Less is More for Reasoning
While conventional wisdom suggests that sophisticated reasoning tasks demand extensive training data (>100, 000 examples), we demonstrate that complex mathematical reasoning abilities can be effectively elicited with surprisingly few examples.
Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning
In this paper, we experimentally demonstrate that, while directly applying DBA to decentralized FL, the attack success rate depends on the distribution of attackers in the network architecture.
XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection
Transformers and their variants have achieved great success in speech processing.
Ranked #1 on
Audio Deepfake Detection
on ASVspoof 2021
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection
Sound Event Detection (SED) is challenging in noisy environments where overlapping sounds obscure target events.
Ranked #1 on
Sound Event Detection
on WildDESED
(using extra training data)
Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning
We remark that existing works investigate the phenomenon of weak-to-strong generation in analogous setup (i. e., binary classification), rather than practical alignment-relevant tasks (e. g., safety).
Exploring Text-Queried Sound Event Detection with Audio Source Separation
To address this issue, we propose the text-queried SED (TQ-SED) framework.
Dark Experience for Incremental Keyword Spotting
Spoken keyword spotting (KWS) is crucial for identifying keywords within audio inputs and is widely used in applications like Apple Siri and Google Home, particularly on edge devices.
TF-Mamba: A Time-Frequency Network for Sound Source Localization
We consider the Mamba-based model to analyze spatial features from speech signals by fusing both time and frequency features, and we develop an SSL system called TF-Mamba.
NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis
Although it achieves fast training speed, there is still a lot of room for improvement in its rendering speed due to the per-point MLP executions for implicit multi-level feature aggregation, especially for real-time applications.
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
Based on the intuition that clustering and subsequent backdoor detection can drastically benefit from knowing client data distributions, we propose a novel data distribution inference mechanism.
Where's That Voice Coming? Continual Learning for Sound Source Localization
Sound source localization (SSL) is essential for many speech-processing applications.
Mixstyle based Domain Generalization for Sound Event Detection with Heterogeneous Training Data
This work explores domain generalization (DG) for sound event detection (SED), advancing adaptability towards real-world scenarios.
WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System
This work aims to advance sound event detection (SED) research by presenting a new large language model (LLM)-powered dataset namely wild domestic environment sound event detection (WildDESED).
Ranked #3 on
Sound Event Detection
on WildDESED
UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection
This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios.
FMSG-JLESS Submission for DCASE 2024 Task4 on Sound Event Detection with Heterogeneous Training Dataset and Potentially Missing Labels
Our proposed method shows superior macro-average pAUC and polyphonic SED score performance on the DCASE 2024 Challenge Task 4 validation dataset and public evaluation dataset.
Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learning
These findings highlight the effectiveness of our model advancements in improving speech command recognition for aviation safety and efficiency in noisy, high-stakes environments.
Towards a Client-Centered Assessment of LLM Therapists by Client Simulation
To this end, we adopt LLMs to simulate clients and propose ClientCAST, a client-centered approach to assessing LLM therapists by client simulation.
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions.
Post-hoc and manifold explanations analysis of facial expression data based on deep learning
This study not only advances the application of AI technology in the field of psychology but also provides a new psychological theoretical understanding the information processing of the AI.
A Survey on Long Video Generation: Challenges, Methods, and Prospects
Video generation is a rapidly advancing research area, garnering significant attention due to its broad range of applications.
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e. g., joint location), and may suffer from local information loss and low generalization ability.
A Survey of Lottery Ticket Hypothesis
The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i. e., winning tickets) that can achieve even better performance than the original model when trained in isolation.
Dual Knowledge Distillation for Efficient Sound Event Detection
To address this issue, we introduce a novel framework referred to as dual knowledge distillation for developing efficient SED systems in this work.
Ranked #2 on
Sound Event Detection
on DESED
(using extra training data)
How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation
In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs).
SAI3D: Segment Any Instance in 3D Scenes
Advancements in 3D instance segmentation have traditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories.
Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction
The first step is to reconstruct the latent space representations (LSRs) from the aggregated model updates using a closed-form inversion mechanism, leveraging specially crafted linear layers.
End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context
In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye in an end-to-end learning way, which has not been well concerned yet.
Ranked #1 on
Gaze Estimation
on Gaze360
Multi-Ship Tracking by Robust Similarity metric
The low frame rates and severe image shake caused by wave turbulence in ship datasets often result in minimal, or even zero, Intersection of Union (IoU) between the predicted and detected bounding boxes.
Eyelid’s Intrinsic Motion-aware Feature Learning for Real-time Eyeblink Detection in the Wild
The experiments verify that, our proposition is significantly superior to the state-of-the-art ones, and with real-time running efficiency.
Ranked #1 on
Eyeblink detection
on HUST-LEBW
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image
3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition.
Ranked #7 on
Hand Pose Estimation
on NYU Hands
Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video.
Ranked #1 on
on MPEblink
A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
We propose a simple, yet powerful approach for unsupervised object segmentation in videos.
Ranked #1 on
Unsupervised Video Object Segmentation
on SegTrack v2
(Jaccard (Mean) metric)
PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking
Our results on challenging datasets are on par with previous works that require much more information (training images of the target objects, 3D models, and/or depth data).
Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling
Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set.
Continual Learning For On-Device Environmental Sound Classification
Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification.
CANShield: Deep Learning-Based Intrusion Detection Framework for Controller Area Networks at the Signal-Level
As ordinary injection attacks disrupt the typical timing properties of the CAN data stream, rule-based intrusion detection systems (IDS) can easily detect them.
Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions
It relies on a small set of training objects to learn local object representations, which allow us to locally match the input image to a set of "templates", rendered images of the CAD models for the new objects.
Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment.
DataLab: A Platform for Data Analysis and Intervention
Despite data's crucial role in machine learning, most existing tools and research tend to focus on systems on top of existing data rather than how to interpret and manipulate data.
Re-ranking for image retrieval and transductive few-shot classification
In the problems of image retrieval and few-shot classification, the mainstream approaches focus on learning a better feature representation.
UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method.
1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
We describe our two-stage instance segmentation framework we use to compete in the challenge.
On the Robustness of Reading Comprehension Models to Entity Renaming
We study the robustness of machine reading comprehension (MRC) models to entity renaming -- do models make more wrong predictions when the same questions are asked about an entity whose name has been changed?
Robust Learning with Adaptive Sample Credibility Modeling
For the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus to alleviate the effect from potential hard noisy samples in clean set.
PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
We experimented on Pascal3D+, ObjectNet3D and Pix3D in a cross-dataset fashion, with both seen and unseen classes.
Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos
Through extensive experiments, we show that our method can generate a high-quality training set which significantly boosts the performance of segmenting objects of unseen classes.
ExplainaBoard: An Explainable Leaderboard for NLP
In this paper, we present a new conceptualization and implementation of NLP evaluation: the ExplainaBoard, which in addition to inheriting the functionality of the standard leaderboard, also allows researchers to (i) diagnose strengths and weaknesses of a single system (e. g.~what is the best-performing system bad at?)
Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features.
Partial FC: Training 10 Million Identities on a Single Machine
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Ranked #2 on
Face Identification
on MegaFace
Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019
All methods were based on deep learning and categorized into two groups: multi-model method and single model method.
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation.
Ranked #16 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Pixel-Pair Occlusion Relationship Map(P2ORM): Formulation, Inference & Application
The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images.
ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification
Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner.
P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
Specifically, we first sample seeds from the point clouds in template and search area respectively.
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly.
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task.
Ranked #13 on
Few-Shot Image Classification
on CIFAR-FS 5-way (1-shot)
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
Towards Cognitive Routing based on Deep Reinforcement Learning
Routing is one of the key functions for stable operation of network infrastructure.
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed.
Ranked #1 on
Hand Pose Estimation
on K2HPD
Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects
Most deep pose estimation methods need to be trained for specific object instances or categories.
Comparative evaluation of 2D feature correspondence selection algorithms
Correspondence selection aiming at seeking correct feature correspondences from raw feature matches is pivotal for a number of feature-matching-based tasks.
Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices
Effective and real-time eyeblink detection is of wide-range applications, such as deception detection, drive fatigue detection, face anti-spoofing, etc.
Ranked #2 on
Eyeblink detection
on HUST-LEBW
Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification
Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc.
DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data
We present an event extraction framework to detect event mentions and extract events from the document-level financial news.
Action Recognition for Depth Video using Multi-view Dynamic Images
To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed.
Monocular Relative Depth Perception With Web Stereo Data Supervision
In this paper we study the problem of monocular relative depth perception in the wild.
Performance Evaluation of 3D Correspondence Grouping Algorithms
This paper presents a thorough evaluation of several widely-used 3D correspondence grouping algorithms, motived by their significance in vision tasks relying on correct feature correspondences.
TasselNet: Counting maize tassels in the wild via local counts regression network
To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment.
Predicting Restaurant Consumption Level through Social Media Footprints
Accurate prediction of user attributes from social media is valuable for both social science analysis and consumer targeting.
