Latest Research
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
• ekazakos/temporal-binding-network
• 
We focus on multi-modal fusion for egocentric action recognition, and propose a novel architecture for multi-modal temporal-binding, i. e. the combination of modalities within a range of temporal offsets.
Progressive Face Super-Resolution via Attention to Facial Landmark
• DeokyunKim/Progressive-Face-Super-Resolution
•
Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images.
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods.
Text Summarization with Pretrained Encoders
• nlpyang/PreSumm
•
For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained while the latter is not).
SOTA for Extractive Document Summarization on CNN / Daily Mail (using extra training data)
ABSTRACTIVE TEXT SUMMARIZATION DOCUMENT SUMMARIZATION EXTRACTIVE DOCUMENT SUMMARIZATION
Noise Flow: Noise Modeling with Conditional Normalizing Flows
Modeling and synthesizing image noise is an important aspect in many computer vision applications.
Limited Data Rolling Bearing Fault Diagnosis with Few-shot Learning
IEEE Access 2019 • SNBQT/Limited-Data-Rolling-Bearing-Fault-Diagnosis-with-Few-shot-Learning
In this study, we propose a deep neural network based few-shot learning approach for rolling bearing fault diagnosis with limited data.
Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
• jiahaoLjh/trajectory-pose-3d
•
Although existing CNN-based temporal frameworks attempt to address the sensitivity and drift problems by concurrently processing all input frames in the sequence, the existing state-of-the-art CNN-based framework is limited to 3d pose estimation of a single frame from a sequential input.
InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35. 7 mAP to 37. 9 mAP without modifying the backbone or network structure.
DATA AUGMENTATION INSTANCE SEGMENTATION SEMANTIC SEGMENTATION
Testing Robustness Against Unforeseen Adversaries
• ddkang/advex-uar
•
We construct novel JPEG, Fog, Gabor, and Snow adversarial attacks to simulate unforeseen adversaries and perform a careful study of adversarial robustness against these and existing distortion types.
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
SOTA for Semantic Segmentation on Cityscapes (using extra training data)
OBJECT DETECTION POSE ESTIMATION REPRESENTATION LEARNING SEMANTIC SEGMENTATION