Search Results for author:
Found 77 papers, 35 papers with code
SparseDC: Depth Completion from sparse and non-uniform inputs
The key contributions of SparseDC are two-fold.
Advancing Attack-Resilient Scheduling of Integrated Energy Systems with Demand Response via Deep Reinforcement Learning
Simulation results demonstrate that our method is capable of adequately addressing the uncertainties resulting from RES and loads, mitigating the impact of cyber-attacks on the scheduling strategy, and ensuring a stable demand supply for various energy sources.
Breast Cancer classification by adaptive weighted average ensemble of previously trained models
Our approach is different because it used adaptive average ensemble after training which has increased the performance of evaluation metrics.
Interpretation of the Transformer and Improvement of the Extractor
It has been over six years since the Transformer architecture was put forward.
FedSN: A General Federated Learning Framework over LEO Satellite Networks
To this end, we propose FedSN as a general FL framework to tackle the above challenges, and fully explore data diversity on LEO satellites.
HoloFed: Environment-Adaptive Positioning via Multi-band Reconfigurable Holographic Surfaces and Federated Learning
Our simulation results confirm that HoloFed achieves a 57% lower positioning error variance compared to a beam-scanning baseline and can effectively adapt to diverse environments.
Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities
In both aspects, considering the inherent resource limitations at the edge, we discuss various cutting-edge techniques, including split learning/inference, parameter-efficient fine-tuning, quantization, and parameter-sharing inference, to facilitate the efficient deployment of LLMs.
MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation
Generating dialogue grounded in videos requires a high level of understanding and reasoning about the visual scenes in the videos.
Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding
To tackle this issue we propose a new approach for MAPF where agents are guided to their destination by following congestion-avoiding paths.
OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision
To overcome the challenge in labeling RF imaging given its human incomprehensible nature, OCHID-Fi employs a cross-modality and cross-domain training process.
Attention Is Not All You Need Anymore
Experimental results show that replacing the self-attention mechanism with the SHE evidently improves the performance of the Transformer, whereas the simplified versions of the SHE, i. e., the HE, the WE, and the ME, perform close to or better than the self-attention mechanism with less computational and memory complexity.
The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World
We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world.
AVSegFormer: Audio-Visual Segmentation with Transformer
In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture.
GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
However, the usage of diffusion models to generate the high-quality object detection data remains an underexplored area, where not only image-level perceptual quality but also geometric conditions such as bounding boxes and camera views are essential.
Graph Propagation Transformer for Graph Representation Learning
The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks.
Ranked #2 on
Graph Regression
on PCQM4M-LSC
(Validation MAE metric)
VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
We hope this model can set a new baseline for generalist vision and language models.
Tracking Progress in Multi-Agent Path Finding
Multi-Agent Path Finding (MAPF) is an important core problem for many new and emerging industrial applications.
InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language
Different from existing interactive systems that rely on pure language, by incorporating pointing instructions, the proposed iGPT significantly improves the efficiency of communication between users and chatbots, as well as the accuracy of chatbots in vision-centric tasks, especially in complicated visual scenarios where the number of objects is greater than 2.
Noise-Resistant Multimodal Transformer for Emotion Recognition
To this end, we present a novel paradigm that attempts to extract noise-resistant features in its pipeline and introduces a noise-aware learning scheme to effectively improve the robustness of multimodal emotion understanding.
A Simulation-Augmented Benchmarking Framework for Automatic RSO Streak Detection in Single-Frame Space Images
In our framework, by making the best use of the hardware parameters of the sensor that captures real-world space images, we first develop a high-fidelity RSO simulator that can generate various realistic space images.
DDP: Diffusion Model for Dense Visual Prediction
We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline.
Ranked #2 on
Monocular Depth Estimation
on SUN-RGBD
Multi-band Reconfigurable Holographic Surface Based ISAC Systems: Design and Optimization
Metamaterial-based reconfigurable holographic surfaces (RHSs) have been proposed as novel cost-efficient antenna arrays, which are promising for improving the positioning and communication performance of integrated sensing and communications (ISAC) systems.
AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving
Object detection with on-board sensors (e. g., lidar, radar, and camera) play a crucial role in autonomous driving (AD), and these sensors complement each other in modalities.
Champion Solution for the WSDM2023 Toloka VQA Challenge
In this report, we present our champion solution to the WSDM2023 Toloka Visual Question Answering (VQA) Challenge.
LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension
We show that our model improves over general-domain and single-domain medical and legal language models when processing mixed-domain (personal injury) text.
FPGA-Based In-Vivo Calcium Image Decoding for Closed-Loop Feedback Applications
Our FPGA implementation enables the real-time calcium image decoding with sub-ms processing latency for closed-loop feedback applications.
Pose-disentangled Contrastive Learning for Self-supervised Facial Representation
Self-supervised facial representation has recently attracted increasing attention due to its ability to perform face understanding without relying on large-scale annotated datasets heavily.
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
In this report, we present our champion solutions to five tracks at Ego4D challenge.
Ranked #1 on
State Change Object Detection
on Ego4D
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state.
Ranked #1 on
Instance Segmentation
on COCO test-dev
(APS metric, using extra
training data)
Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and form a comprehensive object representation to achieve better detection performance.
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
Motivated by the progress of visual-language research, we propose that pre-trained language models (e. g., CLIP) can facilitate animal pose estimation by providing rich prior knowledge for describing animal keypoints in text.
Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search
To track the target in a video, current visual trackers usually adopt greedy search for target object localization in each frame, that is, the candidate region with the maximum response score will be selected as the tracking result of each frame.
Vision Transformer Adapter for Dense Predictions
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT).
Ranked #4 on
Semantic Segmentation
on PASCAL Context
Contrastive Boundary Learning for Point Cloud Segmentation
Point cloud segmentation is fundamental in understanding 3D environments.
Ranked #15 on
Semantic Segmentation
on S3DIS Area5
Load-Flow Solvability under Security Constraints in DC Distribution Networks
We present sufficient conditions for the load-flow solvability under security constraints in DC distribution networks.
Low-rank features based double transformation matrices learning for image classification
However, methods based on this technique ignore the pressure on a single transformation matrix due to the complex information contained in the data.
SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection
We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects.
Recurrent Glimpse-based Decoder for Detection with Transformer
Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage.
Ranked #1 on
Object Detection
on COCO
(GFlops metric)
Adv-4-Adv: Thwarting Changing Adversarial Perturbations via Adversarial Domain Adaptation
Whereas adversarial training can be useful against specific adversarial perturbations, they have also proven ineffective in generalizing towards attacks deviating from those used for training.
MoRe-Fi: Motion-robust and Fine-grained Respiration Monitoring via Deep-Learning UWB Radar
Crucial for healthcare and biomedical applications, respiration monitoring often employs wearable sensors in practice, causing inconvenience due to their direct contact with human bodies.
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
We propose an accurate and efficient scene text detection framework, termed FAST (i. e., faster arbitrarily-shaped text detector).
Ranked #2 on
Scene Text Detection
on MSRA-TD500
RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition
Radio-Frequency (RF) based device-free Human Activity Recognition (HAR) rises as a promising solution for many applications.
V2iFi: in-Vehicle Vital Sign Monitoring via Compact RF Sensing
Given the significant amount of time people spend in vehicles, health issues under driving condition have become a major concern.
Enhancing RF Sensing with Deep Learning: A Layered Approach
To better understand this potential, this article takes a layered approach to summarize RF sensing enabled by deep learning.
SiWa: See into Walls via Deep UWB Radar
To this end, we equip SiWa with a deep learning pipeline to parse the rich sensory data.
Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength
Dropout has been commonly used to quantify prediction uncertainty, i. e, the variations of model predictions on a given input example.
Variational Component Decoder for Source Extraction from Nonlinear Mixture
In many practical scenarios of signal extraction from a nonlinear mixture, only one (signal) source is intended to be extracted.
Expression Snippet Transformer for Robust Video-based Facial Expression Recognition
To this end, we propose to decompose each video into a series of expression snippets, each of which contains a small number of facial movements, and attempt to augment the Transformer's ability for modeling intra-snippet and inter-snippet visual relations, respectively, obtaining the Expression snippet Transformer (EST).
Ranked #7 on
Dynamic Facial Expression Recognition
on DFEW
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows
Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency.
Ranked #1 on
Object Tracking
on VisEvent
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World
However, the coordination of hundreds of agents in a real-life setting like a railway network remains challenging and the Flatland environment used for the competition models these real-world properties in a simplified manner.
Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking
In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy.
Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization
(1) We divide input image into small patches and adopt TIN, successfully transferring image style with arbitrary high-resolution.
Symmetry Breaking for k-Robust Multi-Agent Path Finding
During Multi-Agent Path Finding (MAPF) problems, agents can be delayed by unexpected events.
Recent Progress in Appearance-based Action Recognition
Action recognition, which is formulated as a task to identify various human actions in a video, has attracted increasing interest from computer vision researchers due to its importance in various applications.
CL-MAPF: Multi-Agent Path Finding for Car-Like Robots with Kinematic and Spatiotemporal Constraints
In this paper, we give a mathematical formalization of Multi-Agent Path Finding for Car-Like robots (CL-MAPF) problem.
Robotics Multiagent Systems
Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems
Despite deep neural network (DNN)'s impressive prediction performance in various domains, it is well known now that a set of DNN models trained with the same model specification and the same data can produce very different prediction results.
Invertible Neural BRDF for Object Inverse Rendering
We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering, i. e., joint estimation of reflectance and natural illumination from a single image of an object of known geometry.
Block Shuffle: A Method for High-resolution Fast Style Transfer with Limited Memory
This method can act as a plug-in for Fast Style Transfer without any modification to the network architecture.
Model-Free Voltage Regulation of Unbalanced Distribution Network Based on Surrogate Model and Deep Reinforcement Learning
Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage controls, but this is difficult to obtain in practice.
Condensing Two-stage Detection with Automatic Object Key Part Discovery
Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy.
Twisting operators and centralisers of Lie type groups over local rings
We extend the classical result asserting that the twisting operator preserves certain Deligne--Lusztig character values for truncated formal power series; along the way we discuss some properties of centralisers.
Representation Theory
Distributed Voltage Regulation of Active Distribution System Based on Enhanced Multi-agent Deep Reinforcement Learning
This paper proposes a data-driven distributed voltage control approach based on the spectrum clustering and the enhanced multi-agent deep reinforcement learning (MADRL) algorithm.
TextFuseNet: Scene Text Detection with Richer Fused Features
More specifically, we propose to perceive texts from three levels of feature representations, i. e., character-, word- and global-level, and then introduce a novel text representation fusion technique to help achieve robust arbitrary text detection.
Ranked #1 on
Scene Text Detection
on ICDAR 2015
Towards High Performance Human Keypoint Detection
Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance.
Ranked #5 on
Pose Estimation
on COCO test-dev
A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection
Alternatively, to access much more natural-looking pedestrians, we propose to augment pedestrian detection datasets by transforming real pedestrians from the same dataset into different shapes.
Human Keypoint Detection by Progressive Context Refinement
Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance of person instances.
Transition Subspace Learning based Least Squares Regression for Image Classification
Only learning one projection matrix from original samples to the corresponding binary labels is too strict and will consequentlly lose some intrinsic geometric structures of data.
Progressive LiDAR Adaptation for Road Detection
To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises.
Non-negative representation based discriminative dictionary learning for face recognition
In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification.
Fisher Discriminative Least Squares Regression for Image Classification
On one hand, the Fisher criterion improves the intra-class compactness of the relaxed labels during relaxation learning.
Low-Rank Discriminative Least Squares Regression for Image Classification
To solve above problems, we propose a low-rank discriminative least squares regression model (LRDLSR) for multi-class image classification.
Pedestrian Attribute Recognition: A Survey
We also review some popular network architectures which have been widely applied in the deep learning community.
Context Refinement for Object Detection
Current two-stage object detectors, which consists of a region proposal stage and a refinement stage, may produce unreliable results due to ill-localized proposed regions.
An Experimental Survey on Correlation Filter-based Tracking
We find that further improvements for correlation filter-based tracking can be made on estimating scales, applying part-based tracking strategy and cooperating with long-term tracking methods.
MUlti-Store Tracker (MUSTer): A Cognitive Psychology Inspired Approach to Object Tracking
Variations in the appearance of a tracked object, such as changes in geometry/photometry, camera viewpoint, illumination, or partial occlusion, pose a major challenge to object tracking.
Nonparametric Estimation of Band-limited Probability Density Functions
In this paper, a nonparametric maximum likelihood (ML) estimator for band-limited (BL) probability density functions (pdfs) is proposed.
A Nonparametric Bayesian Approach to Uncovering Rat Hippocampal Population Codes During Spatial Navigation
Rodent hippocampal population codes represent important spatial information about the environment during navigation.
