Search Results for author:
Found 62 papers, 25 papers with code
Konwledge-Enabled Diagnosis Assistant Based on Obstetric EMRs and Knowledge Graph
In this paper, we treat the diagnosis assistant as a multi-label classification task and propose a Knowledge-Enabled Diagnosis Assistant (KEDA) model for the obstetric diagnosis assistant.
Learning Multi-scale Spatial-frequency Features for Image Denoising
Recent advancements in multi-scale architectures have demonstrated exceptional performance in image denoising tasks.
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
This work contributes a promising solution for end-to-end LALMs and highlights the critical role of token-based vocoder in enhancing overall performance for AQAA tasks.
Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction
To tackle the issue, this paper proposes a metric, termed as Trajectory Entropy, to reveal the game status of agents within the level-k game framework.
DGOcc: Depth-aware Global Query-based Network for Monocular 3D Occupancy Prediction
Monocular 3D occupancy prediction, aiming to predict the occupancy and semantics within interesting regions of 3D scenes from only 2D images, has garnered increasing attention recently for its vital role in 3D scene understanding.
Bayesian Optimization for Controlled Image Editing via LLMs
In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning.
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following.
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length.
Systematic Outliers in Large Language Models
Outliers have been widely observed in Large Language Models (LLMs), significantly impacting model performance and posing challenges for model compression.
Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking
These temporal information tokens are used to guide the localization of the target in the next time state, establish long-range contextual relationships between video frames, and capture the temporal trajectory of the target.
Ranked #5 on
Rgb-T Tracking
on LasHeR
Monocular Lane Detection Based on Deep Learning: A Survey
Lane detection plays an important role in autonomous driving perception systems.
Transfer Learning in Vocal Education: Technical Evaluation of Limited Samples Describing Mezzo-soprano
Vocal education in the music field is difficult to quantify due to the individual differences in singers' voices and the different quantitative criteria of singing techniques.
Disambiguating Monocular Reconstruction of 3D Clothed Human with Spatial-Temporal Transformer
Simultaneously, to compensate for local ambiguity in images, a temporal transformer is utilized to extract temporal features from adjacent frames.
The Role of Deductive and Inductive Reasoning in Large Language Models
Large Language Models (LLMs) have achieved substantial progress in artificial intelligence, particularly in reasoning tasks.
MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation
To address the efficiency issue of MESA, we further propose DMESA as its dense counterpart, applying a dense matching framework.
Matlab-based Epoch Extraction for Speaker Differentiation
The number of epochs occurring at similar positions to the reference speaker will be counted as Delta, with larger Delta values indicating greater speaker similarity.
$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models
Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, especially in complex decision-making scenarios, but their static problem-solving strategies often limit their adaptability to dynamic environments.
Hybrid 3D Human Pose Estimation with Monocular Video and Sparse IMUs
On Total Capture dataset, the pose estimation error is significantly decreased compared to the baseline method.
An Embeddable Implicit IUVD Representation for Part-based 3D Human Surface Reconstruction
Recent approaches have combined parametric body models (such as SMPL), which capture body pose and shape priors, with neural implicit functions that flexibly learn clothing details.
MESA: Matching Everything by Segmenting Anything
However, the pervasive presence of matching redundancy between images gives rise to unnecessary and error-prone computations in these methods, imposing limitations on their accuracy.
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Retraining-free is important for LLMs' pruning methods.
RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling
This perception is injected by the Pose Transformer network and learned through a pre-training task that recovers iterative masked joints.
InstructCoder: Instruction Tuning Large Language Models for Code Editing
In this work, we explore the use of Large Language Models (LLMs) to edit code based on user instructions.
Disentangled Counterfactual Reasoning for Unbiased Sequential Recommendation
In this paper, we propose a structural causal model-based method to address the popularity bias issue for sequential recommendation model learning.
Fast Segment Anything
In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.
Ranked #4 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
CodeInstruct: Empowering Language Models to Edit Code
In this work, we explore the use of large language models (LLMs) to edit code based on user instructions, covering a broad range of implicit tasks such as comment insertion, code optimization, and code refactoring.
Self-Evaluation Guided Beam Search for Reasoning
Stochastic beam search balances exploitation and exploration of the search space with temperature-controlled randomness.
Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matching
This paper, thus, pays attention to the search space and proposes to set the initial search space for point matching as the matched image areas containing prominent semantic, named semantic area matches.
TorchBench: Benchmarking PyTorch with High API Surface Coverage
TorchBench is able to comprehensively characterize the performance of the PyTorch software stack, guiding the performance optimization across models, PyTorch framework, and GPU libraries.
FreConv: Frequency Branch-and-Integration Convolutional Networks
In the high-frequency branch, a derivative-filter-like architecture is designed to extract the high-frequency information while a light extractor is employed in the low-frequency branch because the low-frequency information is usually redundant.
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories.
Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up
The gap between the randomly initialized item ID embedding and the well-trained warm item ID embedding makes the cold items hard to suit the recommendation system, which is trained on the data of historical warm items.
Slate-Aware Ranking for Recommendation
Therefore, the ranking stage is still essential for most applications to provide high-quality candidate set for the re-ranking stage.
View Consistency Aware Holistic Triangulation for 3D Human Pose Estimation
The rapid development of multi-view 3D human pose estimation (HPE) is attributed to the maturation of monocular 2D HPE and the geometry of 3D reconstruction.
Balanced Audiovisual Dataset for Imbalance Analysis
We surprisingly find that: the multimodal models with existing imbalance algorithms consistently perform worse than the unimodal one on specific subsets, in accordance with the modality bias.
Movement Enhancement toward Multi-Scale Video Feature Representation for Temporal Action Detection
First, the submergence of movement feature, i. e. the movement information in a snippet is covered by the scene information.
Does Deep Learning REALLY Outperform Non-deep Machine Learning for Clinical Prediction on Physiological Time Series?
In this paper, we systematically examine the performance of machine learning models for the clinical prediction task based on the EHR, especially physiological time series.
Transfering Low-Frequency Features for Domain Adaptation
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision.
FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation
On Total Capture dataset, KineFuse surpasses previous state-of-the-art which uses IMU only for testing by 8. 6\%.
Ranked #2 on
3D Human Pose Estimation
on Total Capture
Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
This paper attempts to tackle the item cold-start problem by generating enhanced warmed-up ID embeddings for cold items with historical data and limited interaction records.
ETAD: Training Action Detection End to End on a Laptop
We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder.
Learning-Based Framework for Camera Calibration with Distortion Correction and High Precision Feature Detection
Therefore, in this paper, we propose a hybrid camera calibration framework which combines learning-based approaches with traditional methods to handle these bottlenecks.
Pruning-aware Sparse Regularization for Network Pruning
MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model.
Estimate Metabolite Taxonomy and Structure with a Fragment-Centered Database and Fragment Network
Metabolite structure identification has become the major bottleneck of the mass spectrometry based metabolomics research.
Adaptive Tree Wasserstein Minimization for Hierarchical Generative Modeling
In this work, we consider OT over tree metrics, which is more general than the sliced Wasserstein and includes the sliced Wasserstein as a special case, and we propose a fast minimization algorithm in $O(n)$ for the optimal Wasserstein-1 transport plan between two distributions in the tree structure.
An End to End Network Architecture for Fundamental Matrix Estimation
In this paper, we present a novel end-to-end network architecture to estimate fundamental matrix directly from stereo images.
Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction
In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment.
Task Decoupled Knowledge Distillation For Lightweight Face Detectors
This method decouples the distillation task of face detection into two subtasks, i. e., the classification distillation subtask and the regression distillation subtask.
A Relaxed Matching Procedure for Unsupervised BLI
Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest.
Parameter Sharing Decoder Pair for Auto Composing
Auto Composing is an active and appealing research area in the past few years, and lots of efforts have been put into inventing more robust models to solve this problem.
Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2
This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2019 Task 1 (\textbf{temporal action proposal generation}) and Task 2 (\textbf{temporal action localization/detection}).
EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection
EdgeStereo also achieves comparable generalization performance for disparity estimation because of the incorporation of edge cues.
A Tangent Distance Preserving Dimensionality Reduction Algorithm
TDPM uses tangent distance instead of geodesic distance, and then applies MDS to the tangent distance matrix to map the manifold into a low dimensional space in which we can get its nonlinear structure.
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization
Weakly supervised temporal action localization, which aims at temporally locating action instances in untrimmed videos using only video-level class labels during training, is an important yet challenging problem in video analysis.
Discriminative Representation Combinations for Accurate Face Spoofing Detection
Secondly we utilize the SSD, which is a deep learning framework for detection, to excavate context cues and conduct end-to-end face presentation attack detection.
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content.
Ranked #3 on
Temporal Action Proposal Generation
on THUMOS' 14
EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching
Recent convolutional neural networks, especially end-to-end disparity estimation models, achieve remarkable performance on stereo matching task.
Face Spoofing Detection by Fusing Binocular Depth and Spatial Pyramid Coding Micro-Texture Features
The second one is a high-level micro-texture based feature called Spatial Pyramid Coding Micro-Texture (SPMT) feature.
Single Shot Temporal Action Detection
The main drawback of this framework is that the boundaries of action instance proposals have been fixed during the classification step.
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection.
Ranked #5 on
Object Detection
on PASCAL VOC 2007
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
In the first stage, a convolutional encoder-decoder sub-network is employed to reconstruct the background images and encode rich prior knowledge of background scenes.
Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
Our approach achieves the state-of-the-art performances on both temporal action proposal task and temporal action localization task.
Ranked #11 on
Temporal Action Proposal Generation
on ActivityNet-1.3
