# Categorical Collections

## Video Retrieval

<details>
<summary>Convolutional Learning of Spatio-temporal Feature</summary>

2010 [paper](https://www.researchgate.net/publication/216792694_Convolutional_Learning_of_Spatio-temporal_Features)
</details>

<details>
<summary>UCF101 A Dataset of 101 Human Actions Classes From Videos in The Wild</summary>

2012 [paper](https://arxiv.org/pdf/1212.0402)
</details>

<details>
<summary>Two-Stream Convolutional Networks for Action Recognition in Videos</summary>

2014 [paper](https://arxiv.org/pdf/1406.2199) [code](https://github.com/jeffreyyihuang/two-stream-action-recognition/tree/master)
</details>

<details>
<summary>Learning Spatiotemporal Features with 3D Convolutional Networks</summary>

2015 [paper](https://arxiv.org/pdf/1412.0767)
</details>

<details>
<summary>Spatiotemporal Residual Networks for Video Action Recognition</summary>

2016 [paper](https://arxiv.org/pdf/1611.02155)
</details>

<details>

<summary>Convolutional Two-Stream Network Fusion for Video Action Recognition</summary>

2016 [paper](https://arxiv.org/pdf/1604.06573) [code](https://github.com/feichtenhofer/twostreamfusion)
</details>

<details>

<summary>Temporal Segment Networks for Action Recognition in Videos</summary>

2017 [paper](https://arxiv.org/pdf/1705.02953) [code](https://github.com/yjxiong/temporal-segment-networks?tab=readme-ov-file#news--updates)
</details>

<details>
<summary>Localizing Moments in Video with Natural Language</summary>

2017 [paper](https://arxiv.org/pdf/1708.01641v1)
</details>

<details>
<summary>A Closer Look at Spatiotemporal Convolutions for Action Recognition</summary>

2018 [paper](https://arxiv.org/pdf/1711.11248v3)
</details>

<details>
<summary>SVD: A Large-Scale Short Video Dataset for Near-Duplicate Video Retrieval</summary>

2019 [paper](https://svdbase.github.io/files/ICCV19_SVD.pdf) [code](https://github.com/4ML-platform/ndvr)
</details>

<details>
<summary>SlowFast Networks for Video Recognition</summary>

2019 [paper](https://arxiv.org/pdf/1812.03982) [code](https://github.com/facebookresearch/SlowFast)
</details>

<details>
<summary>VideoMix: Rethinking Data Augmentation for Video Classification</summary>

2020 [paper](https://arxiv.org/pdf/2012.03457)
</details>

<details>
<summary>Temporal Context Aggregation for Video Retrieval with Contrastive Learning</summary>

2020 [paper](https://arxiv.org/pdf/2008.01334)
</details>

<details>
<summary>TAP-Vid: A Benchmark for Tracking Any Point in a Video</summary>

2023 [paper](https://arxiv.org/pdf/2211.03726) [code](https://github.com/google-deepmind/tapnet)
</details>

<details>
<summary>CoTracker: It is Better to Track Together</summary>

2023 [paper](https://arxiv.org/pdf/2307.07635) [code](https://github.com/facebookresearch/co-tracker)
</details>

<details>
<summary>Revisiting Feature Prediction for Learning Visual Video Representations</summary>

2024 [paper](https://arxiv.org/pdf/2404.08471v1) [code](https://github.com/facebookresearch/jepa/tree/main)
</details>

<details>
<summary>Scaling Foundation Models For Multimodal Video Understanding</summary>

2024 [paper](https://arxiv.org/pdf/2403.15377v3) [code](https://github.com/opengvlab/internvideo)
</details>

<details>
<summary>LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment</summary>

2024 [paper](https://arxiv.org/pdf/2310.01852) [code](https://github.com/PKU-YuanGroup/LanguageBind?tab=readme-ov-file)
</details>

### Others Resources

<details>
<summary>Pytorch Video</summary>

[repository](https://github.com/facebookresearch/pytorchvideo) [document](https://pytorchvideo.org)
</details>

<details>
<summary>Frame Extractor</summary>

[code 1](https://github.com/titania7777/FrameExtractor) [code 2](https://github.com/fastcatai/frame-extraction/blob/master/extract.py)
</details>

<details>
<summary>Katna library</summary>

[repository](https://github.com/keplerlab/katna/tree/master) [document](https://katna.readthedocs.io/en/latest/index.html)
</details>

<details>
<summary>SOTA of DiDeMo</summary>

[paper-with-code](https://paperswithcode.com/sota/zero-shot-video-retrieval-on-didemo?p=languagebind-extending-video-language)
</details>

## Computer Vision
### Image Classification

### Object Detection
<details>
<summary>Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks</summary>

[paper](https://arxiv.org/pdf/1506.01497)
</details>

<details>
<summary>SSD: Single Shot MultiBox Detector</summary>

[paper](https://arxiv.org/pdf/1512.02325)
</details>

<details>
<summary>Other resouces</summary>

[d2l-object-detection](https://d2l.ai/chapter_computer-vision/bounding-box.html)
</details>

### Segmentation

<details>
<summary>TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation</summary>

[paper](https://arxiv.org/pdf/2102.04306) [code](https://github.com/Beckschen/TransUNet)
</details>

<details>
<summary>Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation</summary>

[paper](https://arxiv.org/pdf/2105.05537) [code](https://github.com/HuCaoFighting/Swin-Unet)
</details>

### Image-Text Retrieval
<details>
<summary>SAM - Segment Anything </summary>

[paper](https://arxiv.org/pdf/2304.02643) [code](https://github.com/facebookresearch/segment-anything)
</details>

<details>
<summary>SAM 2: Segment Anything in Images and Videos </summary>

[paper](https://arxiv.org/pdf/2408.00714) [code](https://github.com/facebookresearch/segment-anything-2)
</details>

<details>
<summary>Grounding DINO: DINO with Grounded Pre-Training for Open-Set Object Detection </summary>

[paper](https://arxiv.org/pdf/2303.05499) [code](https://github.com/IDEA-Research/GroundingDINO) [demo](https://huggingface.co/docs/transformers/en/model_doc/grounding-dino)
</details>

<details>
<summary>SlimSAM: 0.1% Data Makes Segment Anything Slim</summary>

[paper](https://arxiv.org/pdf/2312.05284) [code](https://github.com/czg1225/SlimSAM) [demo](https://huggingface.co/Zigeng/SlimSAM-uniform-50)
</details>

<details>
<summary>CLIP - Learning Transferable Visual Models From Natural Language Supervision </summary>

[paper](https://arxiv.org/pdf/2103.00020) [code](https://github.com/openai/CLIP) [demo](https://huggingface.co/docs/transformers/model_doc/clip)
</details>

<details>
<summary>Open CLIP - Reproducible scaling laws for contrastive language-image learning </summary>

[paper](https://arxiv.org/pdf/2212.07143) [code](https://github.com/mlfoundations/open_clip)
</details>

<details>
<summary>GLIGEN: Open-Set Grounded Text-to-Image Generation </summary>

[paper](https://arxiv.org/abs/2301.07093) [code](https://github.com/microsoft/GLIP)
</details>

<details>
<summary>DINO: End-to-End Object Detection with Transformers </summary>

[paper](https://arxiv.org/pdf/2005.12872) [code](https://github.com/facebookresearch/detr)
</details>

<details>
<summary>DINOv2: Learning Robust Visual Features without Supervision </summary>

[paper](https://arxiv.org/pdf/2304.07193) [code](https://github.com/purnasai/Dino_V2)
</details>

<details>
<summary>Prismatic VLMs: The Design Space of Visually-Conditioned Language Models </summary>

[paper](https://arxiv.org/pdf/2402.07865) [code](https://github.com/TRI-ML/prismatic-vlms)
</details>

<details>
<summary>Improved Baselines with Visual Instruction Tuning </summary>

[paper](https://arxiv.org/pdf/2310.03744) [code](https://llava-vl.github.io) [model](https://llava-vl.github.io) [dataset](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K)
</details>

<details>
<summary>OpenVLA: An Open-Source Vision-Language-Action Model </summary>

[paper](https://arxiv.org/pdf/2406.09246) [code](https://github.com/openvla/openvla)
</details>

<details>
<summary>Nomic Embed: Training a Reproducible Long Context Text Embedder </summary>

[paper](https://arxiv.org/pdf/2402.01613)
</details>

<details>
<summary>MetaFormer Is Actually What You Need for Vision </summary>

[paper](https://arxiv.org/pdf/2111.11418) [code](https://github.com/sail-sg/poolformer)
</details>

<details>
<summary>Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs </summary>

[paper](https://arxiv.org/pdf/2401.06209v1) [code](https://github.com/facebookresearch/detr)
</details>

<details>
<summary>Other Resources</summary>

[Dinov2 Image Retrieval Roboflow](https://github.com/roboflow/notebooks/blob/main/notebooks/dinov2-image-retrieval.ipynb)
[DinoV2-Image Classification, Retrieval, Visualization, and Paper Review](https://purnasaigudikandula.medium.com/dinov2-image-classification-visualization-and-paper-review-745bee52c826)
[Clip Image Retrieval](https://github.com/purnasai/CLIP_Image_Retrieval)
[Hugging Face Open Clip](https://huggingface.co/models?library=open_clip&sort=trending)
[Timmm Hugging Face Pretrained Models](https://huggingface.co/timm?search_models=siglip)
[Phi-3-vision-128k-instruct-onnx-data](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx-cuda)
[Phi-3-22b-128k](https://huggingface.co/ontocord/phi-3-22b-128k)
[Onnxruntime-genai python examples](https://github.com/microsoft/onnxruntime-genai/tree/main/examples/python)
[NanoLLaVA-1.5](https://huggingface.co/qnguyen3/nanoLLaVA-1.5)
[BitsandBytes Tutorials and Guides](https://huggingface.co/docs/bitsandbytes/main/en/index)
[Quantization Hugging Face Document](https://huggingface.co/docs/transformers/en/main_classes/quantization#transformers.BitsAndBytesConfig)
</details>

<details>
<summary>AWS Deployment</summary>

[Lambda Handler Tutorial](https://testdriven.io/blog/ml-model-aws-lambda/)
[Serverless Framework Document](https://www.serverless.com/framework/docs)
[Serverless Python Examples](https://github.com/serverless/examples/tree/v4/aws-python-http-api)
</details>

## Natural Language Processing

## 3D Deep Learning

## Quantization

## Mathematics
### (Mixed) Integer Programming
<details>
<summary>Illinois Integer Programming Lectures Notes</summary>

[lecture-notes](https://karthik.ise.illinois.edu/courses/ie511/ie511-sp-21.html)
</details>

<details>
<summary>MIT Non-linear Programming</summary>

[lecture-notes](https://ocw.mit.edu/courses/15-084j-nonlinear-programming-spring-2004/pages/lecture-notes/)
</details>

### Combinatorial Optimization with ML
<details>
<summary>Embedded Mixed-Integer Quadratic Optimization Using the OSQP Solver</summary>

[paper](https://cse.lab.imtlucca.it/~bemporad/publications/papers/ecc18-miosqp.pdf) [miosqp](https://github.com/osqp/miosqp/tree/master)
</details>

<details>
<summary>Exact Combinatorial Optimization with Graph Convolutional Neural Networks</summary>

[paper](https://arxiv.org/pdf/1906.01629v3) [learn2branch](https://github.com/ds4dm/learn2branch) [neurips2019](https://github.com/audreyanneguindon/NeurIPS_2019)
</details>

<details>
<summary>Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies</summary>

[paper](https://arxiv.org/pdf/2002.05120) [branch-search-trees](https://github.com/ds4dm/branch-search-trees)
</details>

<details>
<summary>Learning to Pivot as a Smart Expert</summary>

[paper](https://arxiv.org/pdf/2308.08171)
</details>

## Graph Convolutional Neural Network

<details>
<summary>Semi-Supervised Classification with Graph Convolutional Networks</summary>

[paper](https://arxiv.org/pdf/1609.02907) [gcn](https://github.com/tkipf/gcn) [pygcn](https://github.com/tkipf/pygcn) [document](https://tkipf.github.io/graph-convolutional-networks/) [github-topic](https://github.com/topics/graph-convolutional-networks)
</details>

<details>
<summary>Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks</summary>

[paper](https://arxiv.org/pdf/1904.04849v2) [pytorch-geometric](https://github.com/pyg-team/pytorch_geometric)
</details>

<details>
<summary>Graph neural networks: A review of methods and applications</summary>

[paper](https://arxiv.org/pdf/1812.08434v6) [must-read](https://github.com/thunlp/GNNPapers)
</details>

<details>
<summary>On Statistical Learning of Branch and Bound for Vehicle Routing Optimization</summary>

[paper](https://arxiv.org/pdf/2310.09986) [ml4prv](https://github.com/isotlaboratory/ml4vrp?tab=readme-ov-file)
</details>

<details>
<summary>Modeling Polypharmacy Side Effects with Graph Convolutional Networks</summary>

[paper](https://arxiv.org/pdf/2310.09986) [decagon](https://github.com/mims-harvard/decagon) [document](https://snap.stanford.edu/decagon/)
</details>

<details>
<summary>Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation</summary>

[paper](https://arxiv.org/pdf/1806.02473) [rl_graph_generation](https://github.com/bowenliu16/rl_graph_generation/tree/master)
</details>

<details>
<summary>DGL: A Graph-Centric, Highly-Performant Package for Graph Neural Networks</summary>

[paper](https://arxiv.org/pdf/1909.01315) [dgl](https://github.com/dmlc/dgl/tree/master)
</details>

<details>
<summary>Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation</summary>

[paper](https://arxiv.org/pdf/1806.02473) [rl_graph_generation](https://github.com/bowenliu16/rl_graph_generation/tree/master)
</details>

<details>
<summary>Inductive Representation Learning on Large Graph (GraphSAGE)</summary>

[paper](https://arxiv.org/pdf/1806.02473) [dgl-graphsage](https://github.com/dmlc/dgl/tree/master/examples/pytorch/graphsage)
</details>

<details>
<summary>Other Resources</summary>

[optimization](https://github.com/francisadrianviernes/Optimization/tree/main)
[gilp](https://github.com/engri-1101/gilp) [tsp-solver](https://github.com/mostafabahri/tsp-solver)
</details>

### Computer Graphics

<details>
<summary>Affine Transformation</summary>

[Blog](https://www.algorithm-archive.org/contents/affine_transformations/affine_transformations.html) [Video](https://www.youtube.com/watch?v=AheaTd_l5Is&t=13s)
</details>