ECCV 2018 accepted papers on Video
104 of the 776 papers accepted at ECCV 2018 (13.4%) are on Video, compared with 10.8% at ECCV 2016. They fall into 4 topics.
See ECCV 2018 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Video segmentation and tracking · 46 papers
- DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks (748 citations)
- YouTube-VOS: Sequence-to-Sequence Video Object Segmentation (646 citations)
- Learning Blind Video Temporal Consistency (439 citations)
- Tracking Emerges by Colorizing Videos (403 citations)
- Recycle-GAN: Unsupervised Video Retargeting (345 citations)
- Video Compression through Image Interpolation (342 citations)
- Video Summarization Using Fully Convolutional Sequence Networks (302 citations)
- VideoMatch: Matching based Video Object Segmentation (274 citations)
- Learning to Separate Object Sounds by Watching Unlabeled Video (267 citations)
- Fully Motion-Aware Network for Video Object Detection (213 citations)
- Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation (212 citations)
- Video Object Detection with an Aligned Spatial-Temporal Memory (204 citations)
and 34 more in the interactive map.
Action recognition · 35 papers
- Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification (1,608 citations)
- BSN: Boundary Sensitive Network for Temporal Action Proposal Generation (819 citations)
- Videos as Space-Time Region Graphs (795 citations)
- Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning (423 citations)
- RESOUND: Towards Action Recognition without Representation Bias (358 citations)
- W-TALC: Weakly-supervised Temporal Activity Localization and Classification (350 citations)
- In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video (326 citations)
- AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos (291 citations)
- Compound Memory Networks for Few-shot Video Classification (254 citations)
- Multi-Fiber Networks for Video Recognition (244 citations)
- Actor-centric Relation Network (235 citations)
- Learning to Anonymize Faces for Privacy Preserving Action Detection (221 citations)
and 23 more in the interactive map.
Video-language understanding · 16 papers
- Temporal Relational Reasoning in Videos (1,127 citations)
- ECO: Efficient Convolutional Network for Online Video Understanding (548 citations)
- Less is More: Picking Informative Frames for Video Captioning (226 citations)
- Cross-Modal and Hierarchical Modeling of Video and Text (178 citations)
- Object Level Visual Reasoning in Videos (163 citations)
- Retrospective Encoders for Video Summarization (133 citations)
- Move Forward and Tell: A Progressive Generator of Video Descriptions (123 citations)
- Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior (89 citations)
- Imagine This! Scripts to Compositions to Videos (81 citations)
- Find and Focus: Retrieve and Localize Video Events with Natural Language Queries (76 citations)
- Video Re-localization (71 citations)
- Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos (67 citations)
and 4 more in the interactive map.
Video generation · 7 papers
- X2Face: A network for controlling face generation using images, audio, and pose codes (432 citations)
- Lip Movements Generation at a Glance (283 citations)
- ReenactGAN: Learning to Reenact Faces via Boundary Transfer (209 citations)
- Pose Guided Human Video Generation (142 citations)
- Deep Video Generation, Prediction and Completion of Human Action Sequences (141 citations)
- Learning to Forecast and Refine Residual Motion for Image-to-Video Generation (99 citations)
- Probabilistic Video Generation using Holistic Attribute Control (66 citations)
