Pre-CVPR@NTU

Research Sharing Seminar

May 31, 2023

Agenda

Seminar

Agenda

Registration (08:30am - 09:00am)
Opening Remarks - Chen Change Loy (09:00am - 09:10am)
Invited Talk (09:10am - 10:20am)
Time	Speaker	Title
09:10am - 09:40am	En Jun Choong	An Applied Perspective on Foundation Models and Multimodality
09:40am - 10:20am	Mike Zheng Shou	Multimodal Video Intelligence
Break (10:20am - 10:35am)
Poster Pitches - Section A (10:35am - 10:55am)
Order	Speaker	Title
1	Size Wu	Aligning Bag of Regions for Open-Vocabulary Object Detection
2	Wei Li	Correlational Image Modeling for Self-Supervised Visual Pre-Training
3	Wei Li	Siamese DETR
4	Sijie Wang	HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
5	Ruibo Li	Weakly Supervised Class-agnostic Motion Prediction for Autonomous Driving
6	Jingyi Zhang	UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration
7	Jingyi Zhang	DA-DETR: Domain Adaptive Detection Transformer with Information Fusion
8	Zhipeng Luo	Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
Poster Pitches - Section B (10:55am - 11:20am)
Order	Speaker	Title
9	Muli Yang	Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery
10	Zhongqi Yue	Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
11	Zixuan Fu	sRGB Real Noise Synthesizing with Neighboring Correlation-Aware Noise Model
12	Lanqing Guo	ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
13	Yi Yu	Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
14	Yufei Wang	Raw Image Reconstruction with Learned Compact Metadata
15	Zongrui Li	DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering
16	Yuekun Dai	Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
17	Xiaoming Li	Learning Generative Structure Prior for Blind Text Image Super-resolution
Poster Pitches - Section C (11:20am - 11:40am)
Order	Speaker	Title
18	Yushi Lan	Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion
19	Jingkang Yang	Panoptic Video Scene Graph Generation
20	Chang Liu	GRES: Generalized Referring Expression Segmentation
21	Zhe Jun Tang	ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field
22	Xingyi Li	3D Cinemagraphy from a Single Image
23	Ziqi Huang	Collaborative Diffusion for Multi-Modal Face Generation and Editing
24	Tianxing Wu	Detecting and Grounding Multi-Modal Media Manipulation
25	Peng Wang	F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
Poster Session + Lunch/Refreshment (Sponsored by Huawei) (11:40am - 13:30pm)

Event

Sponsor