ICCV 2017 accepted papers on Video
94 of the 621 papers accepted at ICCV 2017 (15.1%) are on Video. They fall into 4 topics.
See ICCV 2017 in the interactive map
Submitting to ICCV? Checklist →
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 · 47 papers
- Video Frame Synthesis Using Deep Voxel Flow (789 citations)
- Video Frame Interpolation via Adaptive Separable Convolution (770 citations)
- Detail-Revealing Deep Video Super-Resolution (585 citations)
- SegFlow: Joint Learning for Video Object Segmentation and Optical Flow (459 citations)
- Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-Identification (373 citations)
- Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-Identification (358 citations)
- Unmasking the Abnormal Events in Video (356 citations)
- Dual Motion GAN for Future-Flow Embedded Video Prediction (350 citations)
- Learning Video Object Segmentation With Visual Memory (348 citations)
- The Pose Knows: Video Forecasting by Generating Pose Futures (343 citations)
- Learning Deep Neural Networks for Vehicle Re-ID With Visual-Spatio-Temporal Path Proposals (315 citations)
- A Two Stream Siamese Convolutional Neural Network for Person Re-Identification (294 citations)
and 35 more in the interactive map.
Action recognition · 35 papers
- Learning Spatio-Temporal Representation With Pseudo-3D Residual Networks (1,975 citations)
- Temporal Action Detection With Structured Segment Networks (942 citations)
- R-C3D: Region Convolutional 3D Network for Temporal Activity Detection (793 citations)
- View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition From Skeleton Data (694 citations)
- Unsupervised Representation Learning by Sorting Sequences (542 citations)
- TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals (503 citations)
- Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks (437 citations)
- Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos (389 citations)
- Action Tubelet Detector for Spatio-Temporal Action Localization (338 citations)
- Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction (285 citations)
- Temporal Context Network for Activity Localization in Videos (271 citations)
- Chained Multi-Stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection (248 citations)
and 23 more in the interactive map.
Video-language understanding · 11 papers
- The "Something Something" Video Database for Learning and Evaluating Visual Common Sense (1,590 citations)
- Dense-Captioning Events in Videos (1,352 citations)
- Localizing Moments in Video With Natural Language (1,045 citations)
- TALL: Temporal Activity Localization via Language Query (950 citations)
- Attention-Based Multimodal Fusion for Video Description (407 citations)
- What Actions Are Needed for Understanding Human Actions in Videos? (116 citations)
- Weakly Supervised Summarization of Web Videos (103 citations)
- Spatio-Temporal Person Retrieval via Natural Language Queries (63 citations)
- Temporal Tessellation: A Unified Approach for Video Analysis (37 citations)
- Leveraging Weak Semantic Relevance for Complex Video Event Classification (11 citations)
- Video Fill in the Blank Using LR/RL LSTMs With Spatial-Temporal Attentions (10 citations)
Video generation · 1 paper
- Attentive Semantic Video Generation Using Captions (69 citations)
