Research map / Detection and segmentation / CNN features
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add flow-guided feature warping and recurrent temporal encoding to DSS | DSS · DAVIS | maxF: 0.775 -> 0.798 | Improved |
| Add flow-guided feature warping and recurrent temporal encoding to DSS | DSS · DAVIS | MAE: 0.047 -> 0.032 | Improved |
| Add flow-guided feature warping and recurrent temporal encoding to DSS | DSS · FBMS | maxF: 0.760 -> 0.783 | Improved |
| Add flow-guided feature warping and recurrent temporal encoding to DSS | DSS · FBMS | MAE: 0.077 -> 0.063 | Improved |
| Replace temporal modeling with naive weighted feature aggregation (ablation) | DSS video model · DAVIS | maxF: 0.775 -> 0.768 | Hurt |
| Add flow-guided feature warping to LSTM temporal encoding (ablation) | DSS video model · DAVIS | maxF: 0.777 -> 0.793 | Improved |
| Add reverse-LSTM optical-flow refinement to warping plus LSTM (ablation) | DSS video model · DAVIS | maxF: 0.793 -> 0.798 | Improved |
| Add reverse-LSTM optical-flow refinement to warping plus LSTM (ablation) | DSS video model · DAVIS | MAE: 0.035 -> 0.032 | Improved |
| Use LSTM encoding without optical flow or warping (ablation) | DSS video model · DAVIS | maxF: 0.775 -> 0.777 | Improved |
| Use LSTM encoding without optical flow or warping (ablation) | DSS video model · DAVIS | MAE: 0.047 -> 0.036 | Improved |
| Use flow-guided warping in place of unaligned weighted feature aggregation (ablation) | DSS video model · DAVIS | maxF: 0.768 -> 0.780 | Improved |
| Use flow-guided warping in place of unaligned weighted feature aggregation (ablation) | DSS video model · DAVIS | MAE: 0.052 -> 0.036 | Improved |
Closest papers by meaning
- Motion Guided Attention for Video Salient Object Detection (ICCV 2019 · similarity 0.91)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.90)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.90)
- Salient Object Detection with Recurrent Fully Convolutional Networks (TPAMI 2018 · similarity 0.90)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.89)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
