gkioxari / RstarCNN
R*CNN
☆132Updated 7 years ago
Related projects: ⓘ
- Unsupervised Learning using Videos (ICCV 2015)☆174Updated 6 years ago
- Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an exampl…☆175Updated 5 years ago
- Trajectory-pooled Deep-Convolutional Descriptors☆104Updated 7 years ago
- ☆181Updated 7 years ago
- source code for Finding Action Tubes, CVPR 2015☆65Updated 8 years ago
- Code for training py-faster-rcnn and py-R-FCN on multiple GPUs in caffe☆193Updated 7 years ago
- Creation of LMDB for training a multi-label loss in Caffe☆71Updated 8 years ago
- MR-CNNs for Large-Scale Scene Recognition☆138Updated 5 years ago
- Video detection library☆183Updated 7 years ago
- Implementation of our paper - Recurrent Convolutional Network for Video-based Person Re-Identification☆96Updated 6 years ago
- Appearance-and-Relation Networks☆204Updated 5 years ago
- Weakly Supervised Object Localization with Progressive Domain Adaptation (CVPR 2016)☆62Updated 8 years ago
- Complete Code for "Hard-Aware-Deeply-Cascaded-Embedding"☆97Updated 7 years ago
- ☆128Updated this week
- Deformable Convolutional Networks + MST + Soft-NMS☆235Updated 6 years ago
- ☆59Updated 6 years ago
- SST: Single-Stream Temporal Action Proposals (Official Repo)☆101Updated last year
- Reproduction of Focal-loss on caffe☆140Updated 7 years ago
- ☆131Updated 7 years ago
- CVPR2017 - an ultra-compact bilinear model for fine-grained classification☆149Updated 6 years ago
- Generate Caffe Prototxt for Deep Residual Learning Network☆71Updated 8 years ago
- RPN+BF☆203Updated 7 years ago
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos☆68Updated 6 years ago
- Domain Guided Dropout for Person Re-identification☆232Updated 6 years ago
- Caffe real-time data augmentation on-the-fly!!☆164Updated 8 years ago
- Re-implementation of tripletloss function in FaceNet☆92Updated 7 years ago
- ☆240Updated this week
- ☆21Updated 8 years ago
- code for Two-Stream SR-CNNs for Action Recognition in Videos 2016☆34Updated 5 years ago
- Implementation of Excitation Backprop in Caffe☆109Updated 7 years ago