Oral presentations

The goal of the oral presentations is to carry out a bibliographic study and present the result to the class. You will team in up to two in this work.

Below is a list of papers organized in categories and sub-categories, which can help in finding papers related to each other. Choose a number of papers (not less than two, preferably not more than five) that are related to each other in a clear way. For instance, one is influenced by another, their methods are similar in some respect, they are using the same idea in different ways, or they attack the same problem from different sides. Papers should be interesting and not too hard to follow.

The paper list and its categories and sub-categories are too long and "noisy". There may be important papers missing, and the existing ones may not so relevant, or overlapping across categories. It is there only to help in initiating the study, and is by no means a constraint. You are free to start e.g. at arXiv.org CVPR list, CVF CVPR/ICCV open access, or anywhere else. You are also expected to find papers through citations, see below.

Report your choice by Sunday, December 16 through piazza, so that the whole class is notified. In case of overlap with another team, you may be asked to change your selection.

Study the papers in depth. Find how they are connected. Pay attention to related work and, through citations, try to identify other papers that are more connected or more interesting. Feel free at this point to change your list of papers by removing some you found in the list and adding others that you found through studying. But you should not change the subject of your study entirely.

The presentations are on Monday, January 21.

You will have 8 minutes each for your talk plus 4 minutes for questions from the class, that is 20 minutes per team in total. You are expected to ask questions at other students' presentations. You will be evaluated based on your choice of papers, the way you have connected them into a story, and how you present them. You should focus on the main ideas. Implementation details are irrelevant for instance. Your goal is to present something interesting to your fellow students, so they learn something from your talk.

Action recognition
Convolution
Pooling
Recurrent neural networks
Adversarial examples
Attacks
Defenses
Network sensitivity
Architecture
Cascade
Dense
Residual
Reversible
Classification
Fine-grained
Loss functions
Clustering
Convolution
Adaptive
Capsules
Dilation
Frequency
Graph
Graph/co-ordinates
Group
Non-local
Quantized
Low-rank
Sparse
Structured
Detection
Architecture
Attention
Object proposals
Counting
Non-maximum suppression
Parts-based
Proposal-based
Single-shot
Weakly-supervised
Edge detection
Face
Recognition
Few-shot learning
Invariance
Measuring
Normalization
Rotation
Scale
Learning
Domain adaptation
Incremental
Normalization
Regularization
Network ensembles
Local features
Detection
Multi-task learning
Pose estimation
Humans
Objects
Registration/correspondence
Dense
Parts-based
Retrieval
Fine-tuning
Pooling
Re-ranking
Person re-identification
Saliency
Spatial
Saliency
Unsupervised
Segmentation
Conditional random fields
Deconvolution
Instance
Morphology
Things and stuff
Video
Weakly-supervised
Semi-supervised learning
Geometry/layout
Noisy labels
Open-set recognition
Self-supervised
Video
Shape
3d point clouds
Synthesis
Filtering
Inpainting
Style transfer
Super-resolution
Text
Image captioning
Visual question answering
Tracking
Prediction
Visualization