48 citations · 137 across the 13 of their papers we have counts for
13 papers
EventCLIP: Adapting CLIP for Event-based Object Recognition
Ziyi Wu, Xudong Liu, Igor Gilitschenski
Recent advances in zero-shot and few-shot classification heavily rely on the success of pre-trained vision-language models (VLMs) such as CLIP. Due to a shortage of large-scale dat…
SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Ziyi Wu, Jingyu Hu, Wuyue Lu +2
Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leve…
Breaking Bad: A Dataset for Geometric Fracture and Reassembly
Silvia Sellán, Yun-Chun Chen, Ziyi Wu +2
We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fract…
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
Ziyi Wu, Nikita Dvornik, Klaus Greff +2
Understanding dynamics from visual observations is a challenging problem that requires disentangling individual objects from the scene and learning their interactions. While recent…
Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning
Pengxiang Yan, Ziyi Wu, Mengmeng Liu +3
Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the…
Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network
An Tao, Yueqi Duan, He Wang +5
In this paper, we investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumpti…
Road Network Guided Fine-Grained Urban Traffic Flow Inference
Lingbo Liu, Mengmeng Liu, Guanbin Li +3
Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem, which can help greatly reduce the number of the required traffic monitor…
Instance Similarity Learning for Unsupervised Feature Representation
Ziwei Wang, Yunsong Wang, Ziyi Wu +2
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature spac…
Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
Lingbo Liu, Yuying Zhu, Guanbin Li +3
Metro origin-destination prediction is a crucial yet challenging time-series analysis task in intelligent transportation systems, which aims to accurately forecast two specific typ…
RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge
Bill Yuchen Lin, Ziyi Wu, Yichi Yang +2
Question: I have five fingers but I am not alive. What am I? Answer: a glove. Answering such a riddle-style question is a challenging cognitive process, in that it requires complex…
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
Ziyi Wu, Yueqi Duan, He Wang +2
Point cloud is an important 3D data representation widely used in many essential applications. Leveraging deep neural networks, recent works have shown great success in processing…
BiDet: An Efficient Binarized Object Detector
Ziwei Wang, Ziyi Wu, Jiwen Lu +1
In this paper, we propose a binarized neural network learning method called BiDet for efficient object detection. Conventional network binarization methods directly quantize the we…
CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation
Zhanwei Xu, Ziyi Wu, Jianjiang Feng
In this paper, we propose a novel heart segmentation pipeline Combining Faster R-CNN and U-net Network (CFUN). Due to Faster R-CNN's precise localization ability and U-net's powerf…