Ed Fish's repositories
spatio-temporal-contrastive-film
Unsupervised Film Genre Classification using Spatio-Temporal Contrastive Learning
data-efficient-video-transformers
Three experiments for data efficient video transformers.
spatio-temporal-cropping-tool
A tool for creating spatio-temporal augmented crops from video clips for contrastive learning applications.
collaborative-multi-modal-video-transformer
Experimental: A video transformer network for multi-modal pre-computed embeddings
trailer-recommendation-engine
Basic trailer recommendation engine using transformer network and ANNOY.
ML-Interview-Practice
Common Machine Learning Interview Questions and Answers
myQASR
"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization", Interspeech 2023. The paper has been accepted for publication at the INTERSPEECH 2023 Conference.
semantic-video-visualiser
An interactive visualisation of semantically similar movie trailers.
actionformer_release
Code release for ActionFormer (ECCV 2022)
BIKE
【CVPR'2023】Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
cluster-scripts
Admin scripts for uni NVIDIA-GPU cluster
ed-fish.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
FedProx
Federated Optimization in Heterogeneous Networks (MLSys '20)
leaf
Leaf: A Benchmark for Federated Settings
MOFO
The main contribution is to make self-supervised video representation learning more meaningful by raising awareness of motion data
neurips-challenge-kit
Starting kit for the NeurIPS 2023 unlearning challenge
NIID-Bench
Federated Learning on Non-IID Data Silos: An Experimental Study
pytorch-grad-cam
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
Rust-CUDA
Ecosystem of libraries and tools for writing and executing extremely fast GPU code fully in Rust.
STALE
[ECCV 2022] Official Pytorch Implementation of the paper : " Zero-Shot Temporal Action Detection via Vision-Language Prompting "
udlbook-solutions
Understanding Deep Learning - Simon J.D. Prince
ViFi-CLIP
[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".
Vita-CLIP
Official repository for "Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting" [CVPR 2023]
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
wordle-vocab
The current wordle vocabulary for important wordle research projects