ECCV2018比较有意思的paper

Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural Network
Fighting Fake News: Image Splice Detection via Learned Self-Consistency
Face De-Spoofing: Anti-Spoofing via Noise Modeling
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
Visual Text Correction
Cross-Modal Hamming Hashing
Visual Question Answering as a Meta Learning Task
Unsupervised Hard Example Mining from Videos for Improved Object Detection
Less is More: Picking Informative Frames for Video Captioning
Cross-Modal and Hierarchical Modeling of Video and Text
Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data
Triplet Loss in Siamese Network for Object Tracking
Objects that Sound
Question-Guided Hybrid Convolution for Visual Question Answering
Unpaired Image Captioning by Language Pivoting
Goal-Oriented Visual Question Generation via Intermediate Rewards
An Adversarial Approach to Hard Triplet Generation
The Sound of Pixels
Rethinking the Form of Latent States in Image Captioning
Move Forward and Tell: A Progressive Generator of Video Descriptions
Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval
Deep Cross-Modal Projection Learning for Image-Text Matching
Multimodal Dual Attention Memory for Video Story Question Answering
VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions
Broadcasting Convolutional Network for Visual Relational Reasoning
Deep Attention Neural Tensor Network for Visual Question Answering
Women also Snowboard: Overcoming Bias in Captioning Models
Audio-Visual Event Localization in Unconstrained Videos
Grounding Visual Explanations
Conditional Image-Text Embedding Networks
Stacked Cross Attention for Image-Text Matching
Learning Visual Question Answering by Bootstrapping Hard Attention
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
Constraint-Aware Deep Neural Network Compression
Recurrent Fusion Network for Image captioning
Correcting the Triplet Selection Bias for Triplet Loss
Textual Explanations for Self-Driving Vehicles
Exploring Visual Relationship for Image Captioning
Single Shot Scene Text Retrieval