← Search

Junyu Han

35 accepted papers

2026

TakeAD: Preference-Based Post-Optimization for End-to-End Autonomous Driving With Expert Takeover Data

RA-L 2026

Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers driver-initiated takeovers and system disengagements during closed-loop executio

Cited by 3SourceScholar
2025

World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving

AAAI 2025technical

The Multi-modal Large Language Models (MLLMs) with extensive world knowledge have revitalized autonomous driving, particularly in reasoning tasks within perceivable regions. However, when faced with perception-limited areas (dynamic or static occlusion regions), MLLMs struggle to effectively integra…

Cited by 2SourcePDFScholar
2024

Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection

CVPR 2024poster

We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth supervision derived from pseudo-labels to be noisy leading to significant optimiza…

Cited by 7SourcePDFScholar
2024

KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling

CVPR 2024poster

DETR is a novel end-to-end transformer architecture object detector which significantly outperforms classic detectors when scaling up. In this paper we focus on the compression of DETR with knowledge distillation. While knowledge distillation has been well-studied in classic detectors there is a lac…

Cited by 8SourcePDFScholar
2024

Multi-Domain Incremental Learning for Face Presentation Attack Detection

AAAI 2024technical

Previous face Presentation Attack Detection (PAD) methods aim to improve the effectiveness of cross-domain tasks. However, in real-world scenarios, the original training data of the pre-trained model is not available due to data privacy or other reasons. Under these constraints, general methods for…

Cited by 17SourcePDFScholar
2023

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

CVPR 2023poster

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection ambiguity that selected pseudo labels are less accurate, since…

2023

CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision

ICCV 2023poster

Current state-of-the-art semi-supervised semantic segmentation (SSSS) methods typically adopt pseudo labeling and consistency regularization between multiple learners with different perturbations. Although the performance is desirable, many issues remain: (1) supervisions from a single learner tend…

Cited by 16PDFScholar
2023

Cyclically Disentangled Feature Translation for Face Anti-spoofing

AAAI 2023technical

Current domain adaptation methods for face anti-spoofing leverage labeled source domain data and unlabeled target domain data to obtain a promising generalizable decision boundary. However, it is usually difficult for these methods to achieve a perfect domain-invariant liveness feature disentangleme…

2023

Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection

ICCV 2023poster

Current semi-supervised object detection (SSOD) algorithms typically assume class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets (MSCOCO, etc). This assumption can be easily violated since real world datasets can be extremely class imbalanced in nature, thus making the per…

Cited by 13PDFcodeScholar
2023

Graph Contrastive Learning for Skeleton-based Action Recognition

ICLR 2023poster

In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still $\textit{local}$ since the rich cross-sequence relations hav…

2023

Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

ICCV 2023poster

Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing. It is known that one-to-many assignment, assigning one ground-truth object to multiple predictions, succeeds in detection methods s…

Cited by 160PDFcodeScholar
2023

Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation

ICCV 2023poster

In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically pr…

Cited by 41PDFcodeScholar
2023

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

NeurIPS 2023poster

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure priors offer significant potential. Motivated by this insight…

2023

PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers

CVPR 2023poster

Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE) typically adopt a two-stage strategy, which first detects human instances in each frame and then performs single-person PSE with temporal model. However, the global spatio-temporal context among spatial instances can not…

Cited by 35SourcePDFScholar
2023

Semi-DETR: Semi-Supervised Object Detection With Detection Transformers

CVPR 2023poster

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic c…

Cited by 61SourcePDFScholar
2023

StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training

ICLR 2023poster

In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language modeling, based on text region-level image masking. The proposed…

2022

Expressive Talking Head Generation With Granular Audio-Visual Control

CVPR 2022poster

Generating expressive talking heads is essential for creating virtual humans. However, existing one- or few-shot methods focus on lip-sync and head motion, ignoring the emotional expressions that make talking faces realistic. In this paper, we propose the Granularly Controlled Audio-Visual Talking H…

Cited by 148PDFScholar
2022

Few-Shot Font Generation by Learning Fine-Grained Local Styles

CVPR 2022poster

Few-shot font generation (FFG), which aims to generate a new font with a few examples, is gaining increasing attention due to the significant reduction in labor cost. A typical FFG pipeline considers characters in a standard font library as content glyphs and transfers them to a new target font by e…

Cited by 80PDFcodeScholar
2022

MobileFaceSwap: A Lightweight Framework for Video Face Swapping

AAAI 2022technical

Advanced face swapping methods have achieved appealing results. However, most of these methods have many parameters and computations, which makes it challenging to apply them in real-time applications or deploy them on edge devices like mobile phones. In this work, we propose a lightweight Identity-…

2022

RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer

NeurIPS 2022accept

Recently, transformer-based networks have shown impressive results in semantic segmentation. Yet for real-time semantic segmentation, pure CNN-based approaches still dominate in this field, due to the time-consuming computation mechanism of transformer. We propose RTFormer, an efficient dual-resolut…

2022

Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

NeurIPS 2022accept

Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}. We present a solution to overcome the overfitting problem, le…

2022

StyleSwap: Style-Based Generator Empowers Robust Face Swapping

ECCV 2022poster

"Numerous attempts have been made to the task of person-agnostic face swapping given its wide applications. While existing methods mostly rely on tedious network and loss designs, they still struggle in the information balancing between the source and target faces, and tend to produce visible artifa…

2022

ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval

CVPR 2022poster

Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics. Most of existing cross-modal retrieval approaches ignore the usage of s…

Cited by 79PDFScholar
2021

Dynamic Class Queue for Large Scale Face Recognition in the Wild

CVPR 2021poster

Learning discriminative representation using large-scale face datasets in the wild is crucial for real-world applications, yet it remains challenging. The difficulties lie in many aspects and this work focus on computing resource constraint and long-tailed class distribution. Recently, classificatio…

Cited by 32PDFcodeScholar
2021

FaceController: Controllable Attribute Editing for Face in the Wild

AAAI 2021technical

Face attribute editing aims to generate faces with one or multiple desired face attributes manipulated while other details are preserved. Unlike prior works such as GAN inversion which has an expensive reverse mapping process, we propose a simple feed-forward network to generate high-fidelity manipu…

2021

PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

AAAI 2021technical

The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level anno…

2020

HAMBox: Delving Into Mining High-Quality Anchors on Face Detection

CVPR 2020poster

Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under large pose and scale variations. However, we observe that, more…

Cited by 50PDFScholar
2020

Towards Accurate Scene Text Recognition With Semantic Reasoning Networks

CVPR 2020poster

Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to assist text recognition attracts less attention, only RNN-l…

Cited by 424PDFScholar
2019

ACFNet: Attentional Class Feature Network for Semantic Segmentation

ICCV 2019poster

Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts the global context from a categorical perspective. This class-level…

Cited by 357PDFScholar
2019

Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning

ICCV 2019poster

Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data. To address this issue, we introduce a new large-scale text reading benchmark dataset named Chinese Street View T…

Cited by 63PDFScholar
2019

Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes

CVPR 2019poster

Previous scene text detection methods have progressed substantially over the past years. However, limited by the receptive field of CNNs and the simple representations like rectangle bounding box or quadrangle adopted to describe text, previous methods may fall short when dealing with more challengi…

Cited by 328PDFScholar
2017

WordSup: Exploiting Word Annotations for Character Based Text Detection

ICCV 2017poster

Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks. Among these elements, character is the most basic one for various languages such as Western, Chinese, Japanese, mathematical expression and etc. It is natural and conven…

Cited by 250PDFScholar