Research map / Label-efficient and robust learning / Recognition and long-tail
Summarization and Classification of Wearable Camera Streams by Learning the Distributions Over Deep Features of Out-Of-Sample Image Sequences
Alessandro Perina, Sadegh Mohammadi, Nebojsa Jojic, Vittorio Murino
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 constrained Markov walk (CG -> CGcw), 1 label/class (ablation) | counting grid · AIHS | accuracy: 0.2914 -> 0.3144 | Improved |
| add constrained Markov walk, 3 labels/class (ablation) | counting grid · AIHS | accuracy: 0.3455 -> 0.3627 | Improved |
| add constrained Markov walk, 1 label/class (ablation) | counting grid · MEA | accuracy: 0.7583 -> 0.7646 | Improved |
| add constrained Markov walk, 3 labels/class (ablation) | counting grid · MEA | accuracy: 0.801 -> 0.8140 | Improved |
| add constrained Markov walk, 1 label/class (ablation) | counting grid · Google Glass SetA | accuracy: 0.2001 -> 0.2185 | Improved |
| add constrained Markov walk, 3 labels/class (ablation) | counting grid · Google Glass SetB | accuracy: 0.3028 -> 0.3217 | Improved |
| add constrained Markov walk, full labels, subject A (ablation) | counting grid · Google Glass (full labels) subject A | accuracy: 0.8256 -> 0.8337 | Improved |
| add constrained Markov walk, full labels, subject C (ablation) | counting grid · Google Glass (full labels) subject C | accuracy: 0.7951 -> 0.8103 | Improved |
| add constrained walk for only the first 10% of EM iterations (ablation) | counting grid · AIHS 45-class | accuracy | Improved |
| use CGcw embedding instead of fc6 features with NN, 1 label/class | fc6 features · AIHS | accuracy: 0.1821 -> 0.3144 | Improved |
| use 200D autoencoder instead of CGcw with abundant unlabeled data | CGcw · Google Glass (full labels) subject A | accuracy: 0.8337 -> 0.9390 | Hurt |
| vary grid-window ratio (ablation) | counting grid · AIHS | accuracy: around 3% accuracy | No clear effect |
Closest papers by meaning
- Fast Video Classification via Adaptive Cascading of Deep Models (CVPR 2017 · similarity 0.84)
- Long-Term Recurrent Convolutional Networks for Visual Recognition and Description (TPAMI 2016 · similarity 0.84)
- Intriguing Properties of Generative Classifiers (ICLR 2024 · similarity 0.83)
- Rethinking Generalization in Few-Shot Classification (NeurIPS 2022 · similarity 0.83)
- Logarithmic Lenses: Exploring Log RGB Data for Image Classification (CVPR 2024 · similarity 0.82)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.82)
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.
