Search Results for author:
Found 36 papers, 16 papers with code
The AISP-SJTU Simultaneous Translation System for IWSLT 2022
This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task.
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain.
Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Video
We present HandAvatar, a novel representation for hand animation and rendering, which can generate smoothly compositional geometry and self-occlusion-aware texture.
Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
To ensure optimal consistency, the optimal node is required to be the unique STN.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Place Recognition under Occlusion and Changing Appearance via Disentangled Representations
Place recognition is a critical and challenging task for mobile robots, aiming to retrieve an image captured at the same place as a query image from a database.
Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
Neural Radiance Fields (NeRF) have achieved photorealistic novel views synthesis; however, the requirement of accurate camera poses limits its application.
Frequency-Aware Self-Supervised Monocular Depth Estimation
We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models.
Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios
In this paper, we propose a lightweight system, RDS-SLAM, based on ORB-SLAM2, which can accurately estimate poses and build semantic maps at object level for dynamic scenarios in real time using only one commonly used Intel Core i7 CPU.
Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences
The proposed sparse semantic map-based localization approach is robust against occlusion and long-term appearance changes in the environments.
Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem
In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue.
Ranked #1 on
Unsupervised Monocular Depth Estimation
on Kitti Raw
ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement
In this paper, we propose an efficient structure named Efficient Correspondence Transformer (ECO-TR) by finding correspondences in a coarse-to-fine manner, which significantly improves the efficiency of functional correspondence model.
UC-OWOD: Unknown-Classified Open World Object Detection
In this work, we propose a novel OWOD problem called Unknown-Classified Open World Object Detection (UC-OWOD).
META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs.
TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages
Recently, the structural reading comprehension (SRC) task on web pages has attracted increasing research interests.
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications.
AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning
We allow the effective combination of design experience from different sources, so as to create an effective search space containing a variety of TSF models to support different TSF tasks.
MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image
In this work, we propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence.
Hallucinated Neural Radiance Fields in the Wild
This paper studies the problem of hallucinated NeRF: i. e., recovering a realistic NeRF at a different time of day from a group of tourism images.
Greedy-based Value Representation for Efficient Coordination in Multi-agent Reinforcement Learning
Due to the representation limitation of the joint Q value function, multi-agent reinforcement learning (MARL) methods with linear or monotonic value decomposition can not ensure the optimal consistency (i. e. the correspondence between the individual greedy actions and the maximal true Q value), leading to instability and poor coordination.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection
Fusing the two kinds of data usually helps to improve the detection results.
Probabilistic Human Motion Prediction via A Bayesian Neural Network
The experimental results show that our approach makes the interaction more efficient and safer.
HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration
Our experimental results show that the proposed method is able to perform high-quality restoration for unconstrained underwater images without any supervision.
Word-Free Spoken Language Understanding for Mandarin-Chinese
Spoken dialogue systems such as Siri and Alexa provide great convenience to people's everyday life.
Adaptive Feature Alignment for Adversarial Training
Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.
SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance
Thus, we propose a novel unsupervised FIQA method that incorporates Similarity Distribution Distance for Face Image Quality Assessment (SDD-FIQA).
Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration
In the root-relative mesh recovery task, we exploit semantic relations among joints to generate a 3D mesh from the extracted 2D cues.
WebSRC: A Dataset for Web-Based Structural Reading Comprehension
In this paper, we introduce the task of structural reading comprehension (SRC) on web.
img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators.
Ranked #4 on
Head Pose Estimation
on AFLW2000
S3ML: A Secure Serving System for Machine Learning Inference
We present S3ML, a secure serving system for machine learning inference in this paper.
A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning
Using a gating mechanism that discriminates the unseen samples from the seen samples can decompose the GZSL problem to a conventional Zero-Shot Learning (ZSL) problem and a supervised classification problem.
Reveal of Domain Effect: How Visual Restoration Contributes to Object Detection in Aquatic Scenes
According to our analysis, five key discoveries are reported: 1) Domain quality has an ignorable effect on within-domain convolutional representation and detection accuracy; 2) low-quality domain leads to higher generalization ability in cross-domain detection; 3) low-quality domain can hardly be well learned in a domain-mixed learning process; 4) degrading recall efficiency, restoration cannot improve within-domain detection accuracy; 5) visual restoration is beneficial to detection in the wild by reducing the domain shift between training data and real-world scenes.
Rethinking Temporal Object Detection from Robotic Perspectives
From a robotic perspective, the importance of recall continuity and localization stability is equal to that of accuracy, but the AP is insufficient to reflect detectors' performance across time.
Proportionally Fair Clustering
We extend the fair machine learning literature by considering the problem of proportional centroid clustering in a metric context.
Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos
As for temporal detection in videos, temporal refinement networks (TRNet) and temporal dual refinement networks (TDRNet) are developed by propagating the refinement information across time.
Temporally Identity-Aware SSD with Attentional LSTM
Moreover, we develop a creative temporal analysis unit, namely, attentional ConvLSTM (AC-LSTM), in which a temporal attention mechanism is specially tailored for background suppression and scale suppression while a ConvLSTM integrates attention-aware features across time.
Towards Real-Time Advancement of Underwater Visual Quality with GAN
More specifically, an underwater index is investigated to describe underwater properties, and a loss function based on the underwater index is designed to train the critic branch for underwater noise suppression.
