Search Results for author:
Found 48 papers, 22 papers with code
TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
To address the limitations of traffic prediction from location-bound detectors, we present Geographical Cellular Traffic (GCT) flow, a novel data source that leverages the extensive coverage of cellular traffic to capture mobility patterns.
WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA).
Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
Adversarial robustness poses a critical challenge in the deployment of deep learning models for real-world applications.
Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
Causal Video Question Answering (CVidQA) queries not only association or temporal relations but also causal relations in a video.
MuRAL: Multi-Scale Region-based Active Learning for Object Detection
MuRAL identifies informative regions of various scales to reduce annotation costs for well-learned objects and improve training performance.
Free-form 3D Scene Inpainting with Dual-stream GAN
Thus, we present a novel task named free-form 3D scene inpainting.
Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities.
Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations
As global feature alignment requires the features to preserve the poses of input point clouds and local feature matching expects the features to be invariant to these poses, we propose an SE(3)-equivariant feature extractor to simultaneously generate two types of features.
CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches.
Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping
A spatial AI that can perform complex tasks through visual signals and cooperate with humans is highly anticipated.
Fair Robust Active Learning by Joint Inconsistency
Fairness and robustness play vital roles in trustworthy machine learning.
GenISP: Neural ISP for Low-Light Machine Cognition
We propose to improve generalization to unseen camera sensors by implementing a minimal neural ISP pipeline for machine cognition, named GenISP, that explicitly incorporates Color Space Transformation to a device-independent color space.
MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Moreover, different from conventional pixel-wise positional encodings, we introduce a novel depth positional encoding (DPE) to inject depth positional hints into transformers.
D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation
In the field of domain adaptation, a trade-off exists between the model performance and the number of target domain annotations.
Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation
(3) Learning from a different expert.
3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction
Shifts Challenge: Robustness and Uncertainty under Real-World Distributional Shift is a competition held by NeurIPS 2021.
Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data
We design a new Masked Gradient Update (MGU) module to generate auxiliary data along the boundary of in-distribution data points.
Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
Vehicle velocity and inter-vehicle distance estimation are essential for ADAS (Advanced driver-assistance systems) and autonomous vehicles.
NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset
In our work, we take a closer look at object detection in low light.
Multivariate and Propagation Graph Attention Network for Spatial-Temporal Prediction with Outdoor Cellular Traffic
Furthermore, we propose a new model for multivariate spatial-temporal prediction, mainly consisting of two extending graph attention networks (GAT).
TrUMAn: Trope Understanding in Movies and Animations
By coping with the trope understanding task and enabling the deep cognition skills of machines, data mining applications and algorithms could be taken to the next level.
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Despite the success of deep learning on supervised point cloud semantic segmentation, obtaining large-scale point-by-point manual annotations is still a significant challenge.
S3: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality.
Class-agnostic-Few-shot-Object-Counting
Instead of counting a pre-defined class, our model is able to count instances based on input reference images and reduces the huge cost of data collection, training and parameter tuning for each new object class.
Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining
Most 3D neural networks are trained from scratch owing to the lack of large-scale labeled 3D datasets.
OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded objects.
$S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality.
Dual-Awareness Attention for Few-Shot Object Detection
While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems.
Ranked #9 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Situation and Behavior Understanding by Trope Detection on Films
Experimental result demonstrates that modern models including BERT contextual embedding, movie tag prediction systems, and relational networks, perform at most 37% of human performance (23. 97/64. 87) in terms of F1 score.
End-to-End Video Question-Answer Generation with Generator-Pretester Network
Furthermore, using our generated QA pairs only on the Video QA task, we can surpass some supervised baselines.
Raw Image Deblurring
Therefore, we built a new dataset containing both RAW images and processed sRGB images and design a new model to utilize the unique characteristics of RAW images.
GDN: A Coarse-To-Fine (C2F) Representation for End-To-End 6-DoF Grasp Detection
We proposed an end-to-end grasp detection network, Grasp Detection Network (GDN), cooperated with a novel coarse-to-fine (C2F) grasp representation design to detect diverse and accurate 6-DoF grasps based on point clouds.
Efficient and Phase-aware Video Super-resolution for Cardiac MRI
Cardiac Magnetic Resonance Imaging (CMR) is widely used since it can illustrate the structure and function of heart in a non-invasive and painless way.
Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning
In recent years, few-shot learning problems have received a lot of attention.
Expanding Sparse Guidance for Stereo Matching
The performance of image based stereo estimation suffers from lighting variations, repetitive patterns and homogeneous appearance.
xCos: An Explainable Cosine Metric for Face Verification Task
We study the XAI (explainable AI) on the face recognition task, particularly the face verification here.
Explainable Artificial Intelligence (XAI)
Face Recognition
+1
Indoor Depth Completion with Boundary Consistency and Self-Attention
We utilize self-attention mechanism, previously used in image inpainting fields, to extract more useful information in each layer of convolution so that the complete depth map is enhanced.
Ranked #2 on
Depth Completion
on Matterport3D
A Unified Point-Based Framework for 3D Segmentation
We present a new unified point-based framework for 3D point cloud segmentation that effectively optimizes pixel-level features, geometrical structures and global context priors of an entire scene.
Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
Herein, we propose a new enhancement to convolutional LSTM networks that supports accommodation of multiple convolutional kernels and layers.
Video Question Generation via Cross-Modal Self-Attention Networks Learning
We introduce a novel task, Video Question Generation (Video QG).
Super-Identity Convolutional Neural Network for Face Hallucination
Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information.
Drone-based Object Counting by Spatially Regularized Regional Proposal Network
Existing counting methods often adopt regression-based approaches and cannot precisely localize the target objects, which hinders the further analysis (e. g., high-level understanding and fine-grained classification).
Ranked #8 on
Object Counting
on CARPK
Photo Filter Recommendation by Category-Aware Aesthetic Learning
We conduct experiments on the collected FACD for filter recommendation, and the results show that our proposed category-aware aesthetic learning outperforms aesthetic classification methods (e. g., 12% relative improvement).
De-Hashing: Server-Side Context-Aware Feature Reconstruction for Mobile Visual Search
Based on the hashed binary codes, we propose a de-hashing process that reconstructs BoW by leveraging the computing power of remote servers.
Mediated Experts for Deep Convolutional Networks
Our architecture achieves this with the help of expert networks: A network is trained on a disjoint subset of a given dataset and then run in parallel to other experts during deployment.
Who are the Devils Wearing Prada in New York City?
To answer this question, we design a novel system that consists of three major components: (1) constructing a large dataset from the New York Fashion Shows and New York street chic in order to understand the likely clothing fashion trends in New York, (2) utilizing a learning-based approach to discover fashion attributes as the representative characteristics of fashion trends, and (3) comparing the analysis results from the New York Fashion Shows and street-chic images to verify whether the fashion shows have actual influence on the people in New York City.
Scalable Object Detection by Filter Compression With Regularized Sparse Coding
Our method can reconstruct filters by minimizing score map error, while sparse coding reconstructs filters by minimizing appearance error.
Transfer Learning for Video Recognition with Scarce Training Data for Deep Convolutional Neural Network
The same lack-of-training-sample problem limits the usage of deep models on a wide range of computer vision problems where obtaining training data are difficult.
