ilkerkesen

frozen

A PyTorch implementation of Multimodal Few-Shot Learning with Frozen Language Models with OPT.

GAN

Generative Adversarial Networks in Knet

ViLMA

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models (ICLR 2024, Official Implementation)

bvpr

[MULA Workshop @ CVPR 2022] Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters

euphemism

Official Implementation of "Detecting Euphemisms with Literal Descriptions and Visual Imagery"

.emacs.d

Personal Emacs Configuration

adapter-transformers

Huggingface Transformers + Adapters = ❤️

ilkerkesen

Repository for my bio

intphys

RAM

Recurrent Models of Visual Attention implementation in Julia/Knet

Sloth.jl

Lazy bums' Knet package

Ask-Anything

[VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Awesome-Referring-Image-Segmentation

:books: A collection of papers about Referring Image Segmentation.

caption_metrics

Evaluation Metrics for Image Captioning

ClipBERT

[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.

colorfromlanguage

Code base of the paper : Learning to Color from Language

colorization

Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.

DeepLabV3Plus-Pytorch

DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes

dotfiles

Personal Configuration Files

DRAW

Knet implementation of DRAW: A Recurrent Neural Network For Image Generation

frozen-in-time

Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]

ilkerkesen.github.io

Personal Website

MCQ

Official code for "Bridging Video-text Retrieval with Multiple Choice Questions", CVPR 2022 (Oral).

mPLUG-2

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video (ICML 2023)

pytorch-deeplab-xception

DeepLab v3+ model in PyTorch. Support different backbones.

singularity

[ACL 2023] Official PyTorch code for Singularity model in "Revealing Single Frame Bias for Video-and-Language Learning"

UVR-NMT

Neural Machine Translation with universal Visual Representation (ICLR 2020)

Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

VideoCLIP

VideoCLIP and VLM implementations for custom benchmark (originally it's fairseq).

VindLU