Search Results for author:
Found 28 papers, 15 papers with code
Combining Impression Feature Representation for Multi-turn Conversational Question Answering
Multi-turn conversational Question Answering (ConvQA) is a practical task that requires the understanding of conversation history, such as previous QA pairs, the passage context, and current question.
Efficiently Counting Substructures by Subgraph GNNs without Running GNN on Subgraphs
Among these works, a popular way is to use subgraph GNNs, which decompose the input graph into a collection of subgraphs and enhance the representation of the graph by applying GNN to individual subgraphs.
FlowNAS: Neural Architecture Search for Optical Flow Estimation
To address this issue, we propose a neural architecture search method named FlowNAS to automatically find the better encoder architecture for flow estimation task.
BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework
Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks.
Neural Approximation of Graph Topological Features
Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods.
Cycle Representation Learning for Inductive Relation Prediction
In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology.
A Topological View of Rule Learning in Knowledge Graphs
We propose to collect cycle bases that span the space of cycles.
Adaptive Edge Attention for Graph Matching with Outliers
To explore the potential of edges, EAGM learns edge attention on the assignment graph to 1) reveal the impact of each edge on graph matching, as well as 2) adjust the learning of edge representations adaptively.
Ranked #7 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
CBNet: A Composite Backbone Network Architecture for Object Detection
With multi-scale testing, we push the current best single model result to a new record of 60. 1% box AP and 52. 3% mask AP without using extra training data.
Ranked #11 on
Instance Segmentation
on COCO test-dev
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes
Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models.
MathBERT: A Pre-Trained Model for Mathematical Formula Understanding
Large-scale pre-trained models like BERT, have obtained a great success in various Natural Language Processing (NLP) tasks, while it is still a challenge to adapt them to the math-related tasks.
Automatic Description Construction for Math Expression via Topic Relation Graph
In the Selector, a Topic Relation Graph (TRG) is proposed to obtain the relevant documents which contain the comprehensive information of math expressions.
Community-based Cyberreading for Information Understanding
Although the content in scientific publications is increasingly challenging, it is necessary to investigate another important problem, that of scientific information understanding.
RPATTACK: Refined Patch Attack on General Object Detectors
Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually.
OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy.
Link Prediction with Persistent Homology: An Interactive View
Link prediction is an important learning task for graph-structured data.
ConvMath: A Convolutional Sequence Network for Mathematical Expression Recognition
Despite the recent advances in optical character recognition (OCR), mathematical expressions still face a great challenge to recognize due to their two-dimensional graphical layout.
GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling
Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.
MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion
To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone.
MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection
Feature pyramids are widely exploited in many detectors to solve the scale variation problem for object detection.
Automatic Generation of Headlines for Online Math Questions
Compared to conventional summarization tasks, this task has two extra and essential constraints: 1) Detailed math questions consist of text and math equations which require a unified framework to jointly model textual and mathematical information; 2) Unlike text, math equations contain semantic and structural features, and both of them should be captured together.
CBNet: A Novel Composite Backbone Network Architecture for Object Detection
In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it.
Ranked #43 on
Instance Segmentation
on COCO test-dev
TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning
A dual relation propagation approach is proposed, where relations captured by the generated graph are separately propagated from the seen and unseen subgraphs.
Graph Attribute Aggregation Network with Progressive Margin Folding
Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures.
M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels.
Ranked #145 on
Object Detection
on COCO test-dev
Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database
Specifically, a synthesizing method was proposed to generate well-annotated images containing barcode and QR code labels, which contributes to largely decrease the annotation time.
Mutual Enhancement for Detection of Multiple Logos in Sports Videos
Mutual enhancement is also included in our frame propagation mechanism that improves logo detection by utilizing the continuity of logos across frames.
