# Paper Record

###### tags: `Papers list`

`Basic` : `Paper should be read`
`median` : `median level paper`
`TF` : `Transformer based model`
`NF` : `Not get into further`
`GA` : `A piece of garbage`
`ITI` : `Interesting idea`
`POINTER` : `Latest paper listed`

## Compression

### Image Compression
1. [Variational image compression with a scale hyperprior](https://arxiv.org/abs/1802.01436) **tag: Basic**
2. [Practical Full Resolution Learned Lossless Image Compression](https://arxiv.org/abs/1811.12817) **tag: Basic**
3. [ANFIC](https://arxiv.org/abs/2107.08470) **tag: median**
4. [Lossy Image Compression with Normalizing Flows](https://arxiv.org/abs/2008.10486) **tag: median, NF**
5. [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and
Attention Modules](https://openaccess.thecvf.com/content_CVPR_2020/papers/Cheng_Learned_Image_Compression_With_Discretized_Gaussian_Mixture_Likelihoods_and_Attention_CVPR_2020_paper.pdf) **tag: median**
6. [NLA](https://arxiv.org/abs/1910.06244) **tag: median**
7. [Neural Inter-Frame Compression for Video Coding](https://openaccess.thecvf.com/content_ICCV_2019/papers/Djelouah_Neural_Inter-Frame_Compression_for_Video_Coding_ICCV_2019_paper.pdf) **tag: Basic**
8. [End-to-end Optimized Image Compression](https://arxiv.org/abs/1611.01704) **tag: NF**
9. [Checkboard](https://arxiv.org/abs/2103.15306) **tag: median**
10. [Variable Rate Deep Image Compression with Modulated Autoencoder](https://arxiv.org/abs/1912.05526) **tag: GA**
11. [Generative Adversarial Networks for Extreme Learned Image Compression](https://arxiv.org/abs/1804.02958) **tag: median, GAN**
12. [Integer Discrete Flows and Lossless Compression](https://arxiv.org/abs/1905.07376) **tag
13. [Coarse to fine image compression](https://huzi96.github.io/coarse-to-fine-compression.html)**tag: basic**
14. [Multi-scale and Context-adaptive Entropy Model for Image Compression](https://arxiv.org/abs/1910.07844)**tag:Basic**
15. [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://arxiv.org/abs/2007.08739)**tag**
16. [Transformer based image compression](https://arxiv.org/abs/2111.06707)**tag**
17. [Joint Autoregressive](https://proceedings.neurips.cc/paper/2018/file/53edebc543333dfbf7c5933af792c9c4-Paper.pdf)**tag:basic**
18. [Casual context prediction](https://arxiv.org/pdf/2011.09704.pdf)**tag: ITI**
19. [SandWich image compression](https://hhoppe.com/sandwich.pdf)**tag**
20. [Tiny-LIC .. V1 and V2](https://arxiv.org/abs/2204.11448)**tag: TF**
21. [ELIC](https://arxiv.org/abs/2203.10886)**tag: median, channel-wise**
22. [Universal Deep Image Compression via Content-Adaptive Optimization with Adapters](https://arxiv.org/abs/2211.00918)**tag**
23. [Density Modeling of Images using a Generalized Normalization Transformation](https://arxiv.org/abs/1511.06281)**tag**
24. [Qualcomm transformer-based image compression](https://paperswithcode.com/paper/transformer-based-transform-coding)**tag: TF**
25. [Channel-Level Variable Quantization Network for Deep Image Compression](https://arxiv.org/abs/2007.12619)**tag**
26. [Asymmetric Gained Deep Image Compression With Continuous Rate
Adaptation](https://openaccess.thecvf.com/content/CVPR2021/papers/Cui_Asymmetric_Gained_Deep_Image_Compression_With_Continuous_Rate_Adaptation_CVPR_2021_paper.pdf)**tag**
27. [Joint Global and Local Hierarchical Priors for Learned Image Compression](https://arxiv.org/abs/2112.04487)**tag**
28. [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://arxiv.org/abs/2108.09551)**tag**
29. [Content Adaptive Latents and Decoder for
Neural Image Compression](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780545.pdf)**tag** POINTER

### Video Compression
1. [DVC](https://ieeexplore.ieee.org/document/9072487) **tag: Basic, GA**
2. [Learned Video Compression via Joint Spatial-Temporal Correlation Exploration](https://arxiv.org/abs/1912.06348) **tag: median**
3. [M-LVC](https://openaccess.thecvf.com/content_CVPR_2020/papers/Lin_M-LVC_Multiple_Frames_Prediction_for_Learned_Video_Compression_CVPR_2020_paper.pdf) **tag: median**
4. [LVC](https://arxiv.org/abs/1811.06981) **tag: median**
5. [CANF-VC](https://arxiv.org/abs/2207.05315)**tag: median**
6. [ELF-VC](https://arxiv.org/abs/2104.14335)**tag:median**
7. [TCM](https://arxiv.org/abs/2111.13850)**tag: median**
8. [Alpha-VC](https://arxiv.org/abs/2207.14678)**tag:median**
9. [FVC](https://arxiv.org/abs/2105.09600)**tag**
10. [NVC](https://arxiv.org/abs/2007.04574)**tag:median**
11. [DCVC](https://arxiv.org/pdf/2109.15047.pdf)**tag**
12. [Google VCT](https://arxiv.org/abs/2206.07307)**tag: median**
13. [Generalized Difference Coder: A Novel Conditional Autoencoder Structure for Video Compression](https://arxiv.org/abs/2112.08011)**tag: conditional coding formula**
14. [Boosting neural video codecs by exploiting hierarchical redundancy](https://arxiv.org/abs/2208.04303)**tag**
15. [coarse-to-fine video compression](https://openaccess.thecvf.com/content/CVPR2022/papers/Hu_Coarse-To-Fine_Deep_Video_Coding_With_Hyperprior-Guided_Mode_Prediction_CVPR_2022_paper.pdf)**tag: content-adaptive**
16. [Hybrid Spatial-Temporal Entropy Modelling for
Neural Video Compression](https://arxiv.org/pdf/2207.05894.pdf)**tag: median, ACMMA**
17. [MIMT](https://openreview.net/forum?id=j9m-mVnndbm)**tag: TF, ITI**

### Latent Compression
1. [Back-and-Forth prediction for deep tensor compression](https://arxiv.org/abs/2002.07036) **tag: Basic**
2. [Content Adaptive Optimization for Neural Image Compression](https://arxiv.org/abs/1906.01223)**tag**
3. [Content adaptive and error propagation aware deep video compression](https://arxiv.org/abs/2003.11282)**tag**
4. [Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression](https://arxiv.org/abs/2209.00964)**tag**

### Entropy modeling
1. [EntroFormer](https://arxiv.org/abs/2202.05492)**tag:Basic**
2. [ContextFormer](https://arxiv.org/abs/2203.02452)**tag: TF**
3. [LEARNING ACCURATE ENTROPY MODEL WITH
GLOBAL REFERENCE FOR IMAGE COMPRESSION](https://openreview.net/pdf/06784d9497e2c81c4f81b487b90f789b97d82af0.pdf)**tag**

## Content adaptive
1. [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://openaccess.thecvf.com/content_ICCV_2019/papers/Choi_Variable_Rate_Deep_Image_Compression_With_a_Conditional_Autoencoder_ICCV_2019_paper.pdf)**tag**
2. [Content oriented image compression](https://arxiv.org/abs/2207.14168)**tag**
3. [RaFC](https://arxiv.org/abs/2009.05982) **tag**
4. [Optical Flow and Mode Selection for Learning-based Video Coding](https://arxiv.org/abs/2008.02580)**tag: optical flow**

## Generative model
### Image Generation
1. [Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models](https://arxiv.org/abs/2002.07101) **tag**
2. [Conditional Image Synthesis With Auxiliary Classifier GANs](https://arxiv.org/abs/1610.09585) **tag: median, NF**
3. [Taming Transformers for High-Resolution Image Synthesis](https://arxiv.org/abs/2012.09841)**tag: TF, VQ,

**
4. [Vector Quantized Image-to-Image Translation](https://arxiv.org/abs/2207.13286)**tag**
5. [Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes](https://arxiv.org/abs/2111.12701)**tag**
6. [Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer](https://arxiv.org/abs/2206.04452)**tag: ITI**
7. [Autoregressive Image Generation using Residual Quantization](https://arxiv.org/abs/2203.01941)**tag: RQ-VAE, ITI**
8. [Neural Discrete Representation Learning](https://arxiv.org/abs/1711.00937)**tag: VQ-VAE**
9. [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://arxiv.org/abs/1906.00446)**tag**
10. [Hierarchical Quantized Autoencoders](https://proceedings.neurips.cc/paper/2020/file/309fee4e541e51de2e41f21bebb342aa-Paper.pdf)**tag**

### Video Generation
1. [Stochastic Video Generation with a Learned Prior](https://arxiv.org/abs/1802.07687) **tag: DLP project**
2. [Unsupervised Learning of Video Representations using LSTMs](https://arxiv.org/abs/1502.04681) **tag:DLPHW**

## Optical flow
1. [Scale-space flow for end-to-end optimized video compression](https://openaccess.thecvf.com/content_CVPR_2020/papers/Agustsson_Scale-Space_Flow_for_End-to-End_Optimized_Video_Compression_CVPR_2020_paper.pdf) **tag: DLP final project**
2. [RAFT](https://arxiv.org/abs/2003.12039)**tag**
3. [CRAFT](https://arxiv.org/abs/2203.16896)**tag: TF**
4. [PWC-Net](https://arxiv.org/abs/1709.02371)**tag: Basic**
5. [FlowFormer](https://arxiv.org/abs/2203.16194)**tag**
## Special Technique
1. [Soft then Hard: Rethinking the Quantization in Neural Image Compression](https://arxiv.org/abs/2104.05168) **tag: median**
2. [Confident Adaptive Language Modeling](https://arxiv.org/abs/2207.07061)**tag: ITI**
3. [Swin transformer V2](https://arxiv.org/abs/2111.09883)**tag: ITI**

## Complexity Issue
1. [MLP Transformer](https://arxiv.org/abs/2105.01601) **tag: TF**
2. [Pool Transformer](https://arxiv.org/abs/2111.11418) **tag: TF**
3. [Efficient Transformer](https://arxiv.org/abs/2009.06732) **tag: TF**
4. [Confident Adaptive Language Modeling](https://arxiv.org/abs/2207.07061) **tag: hard**
5. [EfficientFormer](https://arxiv.org/abs/2206.01191)**tag:TF, Basic**
6. [Axial Attention in Multidimensional Transformers](https://arxiv.org/abs/1912.12180)**tag:TF**
7. [Sparse Sinkhorn Attention](https://arxiv.org/abs/2002.11296) **tag: NLP-kind TF**
8. [LongFOrmer](https://arxiv.org/abs/2004.05150)**tag: TF**
9. [Masked autoencoder](https://arxiv.org/abs/2111.06377)**tag:TF**
10. [BeiT](https://arxiv.org/abs/2106.08254)**tag:TF**
11. [Slimmable neural network](https://arxiv.org/abs/1812.08928)**tag: TF**
12. [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://arxiv.org/abs/2112.07658)**tag:TF**
13. [Pyraformer](https://openreview.net/forum?id=0EXmFzUn5I)**tag**
14. [Neighboorhood attention Transformer](https://arxiv.org/abs/2204.07143)**tag: TF**
15. [Adaptive Token Sampling For Efficient Vision Transformers](https://arxiv.org/abs/2111.15667)**tag: TF, ITI**
16. [Max Vit](https://arxiv.org/abs/2204.01697)**tag: TF**
17. [Star-Transformer](https://arxiv.org/abs/1902.09113)**tag: NLP-kind TF**
18. [Dynamic VIt](https://arxiv.org/abs/2106.02034)**tag**
19. [IA-RED2](https://arxiv.org/abs/2106.12620)**tag**

## Detection
1. [Disentangled Representation Learning GAN for Pose-Invariant Face Recognition](https://openaccess.thecvf.com/content_cvpr_2017/papers/Tran_Disentangled_Representation_Learning_CVPR_2017_paper.pdf) **tag: NF**
2. [Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation](https://arxiv.org/abs/1506.07452) **tag: NF**
3. [Deep Learning Markov Random Field for Semantic Segmentation](https://arxiv.org/abs/1606.07230) **tag: median**
4. [Feature Space Optimization for Semantic Video Segmentation](http://vladlen.info/papers/FSO.pdf) **tag: NF, basic**
5. [Semantic Image Segmentation via Deep Parsing Network](https://arxiv.org/abs/1509.02634) **tag: NF, GA**
6. [Class-independent sequential full image segmentation, using a convolutional net that finds a segment within an attention region, given a pointer pixel within this segment](https://arxiv.org/abs/1902.07810) **tag: ItI**
7. [SimMIM: A Simple Framework for Masked Image Modeling](https://arxiv.org/abs/2111.09886)**tag:TF**
8. [Video Swin Transformer](https://arxiv.org/abs/2106.13230)**tag:TF**
9. [Swin Transformer](https://arxiv.org/abs/2103.14030)**tag:basic**
10. [3D huamn pose estimation](https://arxiv.org/abs/1811.11742)**tag: TF**
11. [MultiScale Vision Transformer](https://arxiv.org/abs/2104.11227)**tag:TF**
12. [Axial DeepLab Panoptic Segmentation](https://arxiv.org/abs/2003.07853)**tag:TF**
13. [TubeFormer](https://arxiv.org/abs/2205.15361)**tag:TF**
14. [Video Panoptic segmentation](https://arxiv.org/abs/2006.11339)**tag**
15. [UPSNet: A Unified Panoptic Segmentation Network](https://arxiv.org/abs/1901.03784)**tag**
16. [Video Instance Segmentation using Inter-Frame Communication Transformers](https://arxiv.org/abs/2106.03299)**tag: TF**
17. [DERT](https://arxiv.org/abs/2005.12872)**tag:TF**
18. [Vision Transformer with Deformable transformer](https://arxiv.org/abs/2201.00520)**tag:TF, basic**
19. [Pyramid Vision Transformer](https://arxiv.org/abs/2102.12122)**tag: TF**
20. [Video Transformer Network](https://arxiv.org/abs/2102.00719)**tag: TF**
21. [Max-DeepLab](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_MaX-DeepLab_End-to-End_Panoptic_Segmentation_With_Mask_Transformers_CVPR_2021_paper.pdf)**tag: TF**
22. [YOLOX](https://arxiv.org/abs/2107.08430) **tag**
23. [TransTrack](https://arxiv.org/abs/2012.15460)**tag:TF**
24. [TrackFormer](https://arxiv.org/abs/2101.02702)**tag:TF**
25. [CrossVit](https://arxiv.org/abs/2103.14899)**tag**
26. [CabViT: Cross Attention among Blocks for Vision Transformer](https://arxiv.org/abs/2211.07198)**tag: TF**
27. [Mobile-Former: Bridging MobileNet and Transformer](https://arxiv.org/abs/2108.05895)**tag: modile-net**
## Super resolution
1. [BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment](https://arxiv.org/abs/2204.08332)**tag:TF**

## Coding for machine
1. [SSSIC: Semantics-to-Signal Scalable Image Coding With Learned Structural Representations](https://ieeexplore.ieee.org/document/9585549) **tag: Basic**
2. [Scalable Image Coding for Humans and Machines](https://arxiv.org/abs/2107.08373) **tag**

## Diffusion model
### Diffusion Concept
1. [Diffusion formula inferation](https://lilianweng.github.io/posts/2021-07-11-diffusion-models/#nice) **tag: Basic**
2. [The wake-sleep algorithm for unsupervised neural networks](https://www.cs.toronto.edu/~hinton/csc2535/readings/ws.pdf) **tag**
3. [Context-aware Synthesis for Video Frame Interpolation](https://arxiv.org/abs/1803.10967) **tag: NF**
4. [Variational Diffusion Models](https://arxiv.org/abs/2107.00630) **tag**
5. [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239)**tag:Basic**
6. [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2108.02938) **tag:hard**
7. [Palette: Image-to-Image Diffusion Models](https://arxiv.org/abs/2111.05826) **tag:hard**
8. [Score-Based Generative Modeling through Stochastic Differential Equations](https://arxiv.org/abs/2011.13456) **tag:Very_Hard**
9. [Lossy Compression with Gaussian Diffusion](https://arxiv.org/abs/2206.08889) **tag:median**
10. [Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502) **tag:median**
11. [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://arxiv.org/abs/1503.03585)**tag:Basic**

## Interpolation
1. [Softmax Splatting for Video Frame Interpolation](https://arxiv.org/abs/2003.05534) **tag: DLP final project**
2. [Splatting-based Synthesis for Video Frame Interpolation](https://arxiv.org/pdf/2201.10075v1.pdf) **tag: DLP final project**

## Deep Learning Basic model
1. [GAN](https://arxiv.org/abs/1406.2661) **tag**
2. [Normalizing Flows: An Introduction and Review of Current Methods](https://www.researchgate.net/publication/341222454_Normalizing_Flows_An_Introduction_and_Review_of_Current_Methods) **tag**
3. [ViT](https://arxiv.org/abs/2010.11929) **tag: TF**
4. [Swin Transformer](https://arxiv.org/abs/2103.14030) **tag: Basic, TF**
5. [Pixel Recurrent Neural Networks](https://arxiv.org/abs/1601.06759) **tag: Basic**
6. [PixelCNN](https://arxiv.org/abs/1606.05328) **tag: Basic**
7. [SFT](https://arxiv.org/abs/1804.02815) **tag: basic**
8. [Deformable Convolutional Networks](https://arxiv.org/abs/1703.06211)**tag**
9. [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://arxiv.org/abs/1711.10305)**tag**
10. [Attention is all you need](https://arxiv.org/abs/1706.03762)**tag**
11. [Non-local attention](https://arxiv.org/abs/1711.07971)**tag**
12. [R-CNN](https://arxiv.org/abs/1311.2524)**tag**
13. [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://arxiv.org/abs/1705.07750)**tag**
14. [Gumbel SoftMax](https://arxiv.org/abs/1611.01144)**tag**

## Paper haven't been read
1. [FLOW-GAN](https://arxiv.org/abs/1705.08868)
2. [Variable Rate Image Compression with Recurrent Neural Networks](https://arxiv.org/abs/1511.06085)
3. [Deformable Video Transformer](https://arxiv.org/abs/2203.16795)
4. [LVQ-VAE](https://openreview.net/forum?id=1pGmKJvneD7)

## shakey paper
1. [Density Modeling of Images using a Generalized Normalization Transformation](https://www.researchgate.net/publication/284218796_Density_Modeling_of_Images_using_a_Generalized_Normalization_Transformation) **tag**