Home

Awesome

365 Days Computer Vision Learning LinkedIn Post

Follow me on LinkedIn : https://www.linkedin.com/in/ashishpatel2604/

DaysTopicPost Link
1EfficientDethttps://bit.ly/362NWHa
2Yolact++https://bit.ly/3o5OaU3
3YOLO Serieshttps://bit.ly/3650LAJ
4Detrhttps://bit.ly/39S5F57
5Vision Transformerhttps://bit.ly/39UMHLd
6Dynamic RCNNhttps://bit.ly/3939gy5
7DeiT: (Data-efficient image Transformer)https://bit.ly/363ZABt
8Yolov5https://bit.ly/39QHTXq
9DropBlockhttps://bit.ly/3sM4TiG
10FCNhttps://bit.ly/3iE9U8C
11Unethttps://bit.ly/3izdbG2
12RetinaNethttps://bit.ly/3o5NrlN
13SegNethttps://bit.ly/3qIauVz
14CAMhttps://bit.ly/2Y2I8ZR
15R-FCNhttps://bit.ly/3iCKsQL
16RepVGGhttps://bit.ly/2Y2pGjV
17Graph Convolution Networkhttps://bit.ly/2LS9RK8
18DeconvNethttps://bit.ly/2Mhwzes
19ENethttps://bit.ly/2Y2HgEz
20Deeplabv1https://bit.ly/3o7Utqn
21CRF-RNNhttps://bit.ly/2Y5nsR4
22Deeplabv2https://bit.ly/2Y9DgSx
23DPNhttps://bit.ly/363Cye2
24Grad-CAMhttps://bit.ly/3iF006q
25ParseNethttps://bit.ly/3oesFk5
26ResNeXthttps://bit.ly/2M2sXxe
27AmoebaNethttps://bit.ly/2YgRIbN
28DilatedNethttps://bit.ly/2M9fuDS
29DRNhttps://bit.ly/2KXVmUH
30RefineNethttps://bit.ly/3cpCBVq
31Preactivation-Resnethttps://bit.ly/2MJtgwQ
32SqueezeNethttps://bit.ly/3cv3Ca0
33FractalNethttps://bit.ly/3pSv712
34PolyNethttps://bit.ly/3atCQfJ
35DeepSim(Image Quality Assessment)https://bit.ly/3oKJGTi
36Residual Attention Networkhttps://bit.ly/3cIjupL
37IGCNet / IGCVhttps://bit.ly/36LRfTo
38Resnet38https://bit.ly/2N7tpKL
39SqueezeNexthttps://bit.ly/3cSev5W
40Group Normalizationhttps://bit.ly/3ryNxEI
41ENAShttps://bit.ly/2LB6pDC
42PNASNethttps://bit.ly/3tIX6mx
43ShuffleNetV2https://bit.ly/2Zb3xAM
44BAMhttps://bit.ly/3b67xb2
45CBAMhttps://bit.ly/3plxHvJ
46MorphNethttps://bit.ly/3rWzcSM
47NetAdapthttps://bit.ly/2NtlFmE
48ESPNetv2https://bit.ly/3jWVoJv
49FBNethttps://bit.ly/3k1PXZL
50HideandSeekhttps://bit.ly/3qELCP0
51MR-CNN & S-CNNhttps://bit.ly/2Zw6QTf
52ACoL: Adversarial Complementary Learninghttps://bit.ly/3qKFNiU
53CutMixhttps://bit.ly/2Nt5shI
54ADLhttps://bit.ly/3qNeFQm
55SAOLhttps://bit.ly/2NVuBBs
56SSDhttps://bit.ly/37PWpyo
57NOChttps://bit.ly/3uBrZJJ
58G-RMIhttps://bit.ly/3kJDlap
59TDMhttps://bit.ly/3dV5zgN
60DSSDhttps://bit.ly/3q6EHg8
61FPNhttps://bit.ly/2OewZn0
62DCNhttps://bit.ly/3e3G4Kg
63Light-Head-RCNNhttps://bit.ly/388rtcT
64Cascade RCNNhttps://bit.ly/3uUDlZz
65MegNethttps://bit.ly/3bkNvuM
66StairNethttps://bit.ly/3bluE2P
67ImageNet Rethinkinghttps://bit.ly/3bqBfZZ
68ERFNethttps://bit.ly/2OxgC5c
69LayerCascadehttps://bit.ly/3qzWdd8
70IDW-CNNhttps://bit.ly/3letEAY
71DIShttps://bit.ly/3vi3xh3
72SDNhttps://bit.ly/3lftn0k
73ResNet-DUC-HDChttps://bit.ly/3lmdhlN
74Deeplabv3+https://bit.ly/3lfSRuR
75AutoDeeplabhttps://bit.ly/2P14kSF
76c3https://bit.ly/3qX0yqK
77DRRNhttps://bit.ly/3ltkWP9
78BRยฒNethttps://bit.ly/3f0jGlI
79SDShttps://bit.ly/3f0CZLw
80AdderNethttps://bit.ly/3sfMdYa
81HyperColumnhttps://bit.ly/3vV7Jn5
82DeepMaskhttps://bit.ly/3cY2RVR
83SharpMaskhttps://bit.ly/3rg0h2r
84MultipathNethttps://bit.ly/31fcTMR
85MNChttps://bit.ly/39rRXqj
86InstanceFCNhttps://bit.ly/3wbQuy8
87FCIShttps://bit.ly/3dhPz6B
88MaskLabhttps://bit.ly/3wb3Vya
89PANethttps://bit.ly/2PmQTNs
90CUDMedVision1https://bit.ly/3rETZd1
91CUDMedVision2https://bit.ly/3mago0q
92CFS-FCNhttps://bit.ly/3cXP0zX
93U-net+Res-nethttps://bit.ly/3mpKD3P
94Multi-Channelhttps://bit.ly/2Q1WCbN
95V-Nethttps://bit.ly/3sYxGAt
963D-Unethttps://bit.ly/3uvNOcS
97MยฒFCNhttps://bit.ly/3cXSlPG
98Suggestive Annotationhttps://bit.ly/3t1UbV8
993D Unet + Resnethttps://bit.ly/3wRu3i9
100Cascade 3D-Unethttps://bit.ly/3siNsEX
101DenseVoxNethttps://bit.ly/2RGliYd
102QSA + QNThttps://bit.ly/3wWtyDf
103Attention-Unethttps://bit.ly/3eaMNAK
104RUNet + R2Unethttps://bit.ly/2Q4bIxG
105VoxResNethttps://bit.ly/32gLBWN
106Unet++https://bit.ly/3esShGV
107H-DenseUnethttps://bit.ly/3dN53kn
108DUnethttps://bit.ly/3sPYrWS
109MultiResUnethttps://bit.ly/32J7Epr
110Unet3+https://bit.ly/3vj4lRX
111VGGNet For Covid19https://bit.ly/3ewquW6
112๐——๐—ฒ๐—ป๐˜€๐—ฒ-๐—š๐—ฎ๐˜๐—ฒ๐—ฑ ๐—จ-๐—ก๐—ฒ๐˜ (๐——๐—š๐—ก๐—ฒ๐˜)https://bit.ly/3tR67cM
113Ki-Unethttps://bit.ly/3gD4wDK
114Medical Transformerhttps://bit.ly/3dLw9Zf
115Deep Snake- Instance Segmentationhttps://bit.ly/3dQmdhm
116BlendMaskhttps://bit.ly/32LVXyf
117CenterNethttps://bit.ly/3aJrJQD
118SRCNNhttps://bit.ly/3t82eie
119Swin Transformerhttps://bit.ly/2QMWxct
120Polygon-RNNhttps://bit.ly/3ujEJ7D
121PolyTransformhttps://bit.ly/3gT11ZZ
122D2Dethttps://bit.ly/3b2EDJL
123PolarMaskhttps://bit.ly/3uklSsO
124FGNhttps://bit.ly/3uiyyAl
125Meta-SRhttps://bit.ly/3ekFyr9
126Iterative Kernel Correlationhttps://bit.ly/3xPGZp6
127SRFBNhttps://bit.ly/2Qc1c7z
128ODEhttps://bit.ly/3w1K8k4
129SRNTThttps://bit.ly/2RNT9hS
130Parallax Attentionhttps://bit.ly/3tIr74x
1313D Super Resolutionhttps://bit.ly/3bliXJa
132FSTRNhttps://bit.ly/3uWJ8h7
133PointGrouphttps://bit.ly/2QfeKPP
1343D-MPAhttps://bit.ly/3bqz9J6
135Saliency Propagationhttps://bit.ly/3tXTvj4
136Libra R-CNNhttps://bit.ly/3hDytnt
137SiamRPN++https://bit.ly/33TNjyi
138LoFTRhttps://bit.ly/3eUtlJS
139MZSRhttps://bit.ly/3ul5gAs
140UCTGANhttps://bit.ly/3fQg9ox
141OccuSeghttps://bit.ly/3bUJtta
142LAPGANhttps://bit.ly/3unOjW1
143TPNhttps://bit.ly/3vvyIoW
144GTADhttps://bit.ly/3c09yqK
145SlowFasthttps://bit.ly/3fMrI0d
146IDUhttps://bit.ly/2ROcIa5
147ATSShttps://bit.ly/3hTIflC
148Attention-RPNhttps://bit.ly/3oYescY
149Aug-FPNhttps://bit.ly/3fUbdzi
150Hit-Detectorhttps://bit.ly/3uGCLgB
151MCNhttps://bit.ly/3ySpjtq
152CentripetalNethttps://bit.ly/2S1WNVB
153ROAMhttps://bit.ly/34Ft8Ex
154PF-NET(3D)https://bit.ly/2TzQiK9
155PointAugmenthttps://bit.ly/3uMc8Hr
156C-Flowhttps://bit.ly/3xgDlUn
157RandLA-Nethttps://bit.ly/3fYajD9
158Total3DUnderStandinghttps://bit.ly/3v3jy9c
159IF-Netshttps://bit.ly/3v7XjPj
160PerfectShapehttps://bit.ly/3za20vk
161ACNehttps://bit.ly/3gaJQSN
162PQ-Nethttps://bit.ly/35dVPsm
163SG-NNhttps://bit.ly/3iQ4yca
164Cascade Cost Volumehttps://bit.ly/3gyZHtt
165SketchGCNhttps://bit.ly/3pVoxI8
166Spektral (Graph Neural Network)https://bit.ly/3q2T079
167Graph Convolution Neural Networkhttps://bit.ly/3gAkiNX
168Fast Localized Spectral Filtering(Graph Kernel)https://bit.ly/3iRUEa0
169GraphSAGEhttps://bit.ly/3gCj9Xx
170ARMA Convolutionhttps://bit.ly/3qcubpC
171Graph Attention Networkshttps://bit.ly/3h1gfKy
172Axial-Deeplabhttps://bit.ly/3qiIF7l
173Tidehttps://bit.ly/3j5evmh
174SipMaskhttps://bit.ly/3gMBoJE
175UFOยฒhttps://bit.ly/2SVS2xA
176SCANhttps://bit.ly/2ThBv70
177AABO : Adaptive Anchor Box Optimizationhttps://bit.ly/3qCSRaP
178SimAughttps://bit.ly/3dlV6tK
179Instant-teachinghttps://bit.ly/3h0E2LU
180Refinement Network for RGB-Dhttps://bit.ly/3dtRh5O
181Polka Lineshttps://bit.ly/3hlNbhd
182HOTRhttps://bit.ly/3hsV44i
183Soft-IntroVAEhttps://bit.ly/3jFozTk
184ReXNethttps://bit.ly/3r42WO9
185DiNTShttps://bit.ly/3AQibii
186Pose2Meshhttps://bit.ly/3wFTORi
187Keep Eyes on the Lanehttps://bit.ly/3wxs4hl
188AssembleNet++https://bit.ly/3xAHhjf
189SNE-RoadSeghttps://bit.ly/3hyCEAL
190AdvPChttps://bit.ly/3i3dGrV
191Eagle eyehttps://bit.ly/3e5Iqaz
192Deep Hough Transformhttps://bit.ly/2UEFbAm
193WeightNethttps://bit.ly/3rfDSUL
194StyleMAPGANhttps://bit.ly/2URgPTO
195PD-GANhttps://bit.ly/3xQMCmM
196Non-Local Sparse Attentionhttps://bit.ly/3xJZbAd
197TediGANhttps://bit.ly/3wH67MZ
198FedDGhttps://bit.ly/3zfKiGe
199Auto-Exposure Fusionhttps://bit.ly/3y3F2W1
200Involutionhttps://bit.ly/36Ksiaz
201MutualNethttps://bit.ly/3zhfd4N
202Teachers do more than teach - Image to Image translationhttps://bit.ly/36RP28K
203VideoMoCohttps://bit.ly/3f6Pq7Z
204ArtGANhttps://bit.ly/3rvDCB9
205Vip-DeepLabhttps://bit.ly/3xmzmVX
206PSConvolutionhttps://bit.ly/3rEIgMY
207Deep learning technique on Semantic Segmentationhttps://bit.ly/375hrID
208Synthetic to Realhttps://bit.ly/3yfZSRO
209Panoptic Segmentationhttps://bit.ly/376tbdA
210HistoGANhttps://bit.ly/3zSYyVD
211Semantic Image Mattinghttps://bit.ly/3s5ZD9F
212Anchor-Free Person Searchhttps://bit.ly/2VI0KAD
213Spatial-Phase-Shallow-Learninghttps://bit.ly/3CDAl82
214LiteFlowNet3https://bit.ly/3yDILcO
215EfficientNetv2https://bit.ly/3xAQsiE
216CBNETv2https://bit.ly/3s3ptvb
217PerPixel Classificationhttps://bit.ly/3lOomyg
218Kaleido-BERThttps://bit.ly/3ywh2Lf
219DARKGANhttps://bit.ly/3lTW05J
220PPDMhttps://bit.ly/3lPgjBt
221SEANhttps://bit.ly/3yOUJ3L
222Closed-Loop Mattershttps://bit.ly/3CzBnlq
223Elastic Graph Neural Networkhttps://bit.ly/3jket9S
224Deep Imbalance Regressionhttps://bit.ly/3yn0Ue3
225PIPAL - Image Quality Assessmenthttps://bit.ly/3gCliSx
226Mobile-Formerhttps://bit.ly/3kxCSbm
227Rank and Sort Losshttps://bit.ly/3sPQt1s
228Room Classification using Graph Neural Networkhttps://bit.ly/3gD8Odv
229Pyramid Vision Transformerhttps://bit.ly/3zmod9h
230EigenGANhttps://bit.ly/3BfdIVO
231GNeRFhttps://bit.ly/3mD3kTR
232DetCohttps://bit.ly/3sQiRk9
233DERT with Special Modulated Co-Attentionhttps://bit.ly/3sPQ5jw
Residual Attentionhttps://bit.ly/3yni4bJ
235MG-GANhttps://bit.ly/3mD30o7
236Adaptable GAN Encodershttps://bit.ly/3yh4XJ3
237AdaAttNhttps://bit.ly/3BepKPa
238Conformerhttps://bit.ly/3gCkj4N
239YOLOPhttps://bit.ly/3BicysB
240VMNethttps://bit.ly/3k73jFZ
241Airberthttps://bit.ly/3nvcrGs
242๐—ข๐—ฟ๐—ถ๐—ฒ๐—ป๐˜๐—ฒ๐—ฑ ๐—ฅ-๐—–๐—ก๐—กhttps://bit.ly/397Zius
243Battle of Network Structurehttps://bit.ly/2XcHbB0
244InSeGANhttps://bit.ly/3z9wyMF
245Efficient Person Searchhttps://bit.ly/3CpbZOr
246DeepGCNshttps://bit.ly/3AevSHg
247GroupFormerhttps://bit.ly/3lqzm2Y
248SLIDEhttps://bit.ly/3hwpiEp
249Super Neuronhttps://bit.ly/3zkXE3D
250SOTRhttps://bit.ly/3hvqCYl
251Survey : Instance Segmentationhttps://bit.ly/3k90xQB
252SO-Posehttps://bit.ly/3C56KD8
253CANethttps://bit.ly/2XlDKZ2
254XVFIhttps://bit.ly/3lrOpcZ
255TxThttps://bit.ly/3tGFlEH
256ConvMLPhttps://bit.ly/2XlE8Xu
257Cross Domain Contrastive Learninghttps://bit.ly/3tDb2id
258OS2D: One Stage Object Detectionhttps://bit.ly/3ufnEMD
259PointManifoldCuthttps://bit.ly/3CKvAIL
260Large Scale Facial Expression Datasethttps://bit.ly/2ZqtT4V
261Graph-FPNhttps://bit.ly/2XH8T9f
2623D Shape Reconstructionhttps://bit.ly/2XTe9aq
263Open Graph Benchmark Datasethttps://bit.ly/3ET2Lfl
264ShiftAddNethttps://bit.ly/3i6eb5C
265WatchOut! Motion Blurring the vision of your DNNhttps://bit.ly/3CKTzrw
266Rethinking Learnable Tree Filterhttps://bit.ly/3zHfPAC
267Neuron Merginghttps://bit.ly/39DwLNS
268Distance IOU Losshttps://bit.ly/3i7Zj6z
269Deep Imitation learninghttps://bit.ly/3AzGVd6
270Pixel Level Cycle Associationhttps://bit.ly/3iTZMK6
271Deep Model Fusionhttps://bit.ly/2YK45kl
272Object Representation Networkhttps://bit.ly/3BA0mnE
273HOI Analysishttps://bit.ly/3FH2Key
274Deep Equilibrium Modelshttps://bit.ly/3FDH2IB
275Sampling from k-DPPhttps://bit.ly/3BAyRuc
276Rotated Binary Neural Networkhttps://bit.ly/3mIuYx3
277PP-LCNet - LightCNNhttps://bit.ly/3v1Zh5H
278MC-Net+https://bit.ly/3v5tYqk
279Fake it till you make ithttps://bit.ly/3AyGTSQ
280Enformerhttps://bit.ly/3AAdCr9
281VideoCliphttps://bit.ly/3mOueGu
282Moving Fashionhttps://bit.ly/3jdvAtN
283Convolution to Transformerhttps://bit.ly/3v5yy8f
284HeadGANhttps://bit.ly/3BLzRvm
285Focal Transformerhttps://bit.ly/3lvCYSI
286StyleGAN3https://bit.ly/3kvFPKw
2873Detr:3D Object Detectionhttps://bit.ly/3Hfk6A8
288Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?https://bit.ly/3kyWM6H
289Back to the Featureshttps://bit.ly/3kvsxh3
290Anticipative Video Transformerhttps://bit.ly/30mADl2
291Attention Meets Geometryhttps://bit.ly/3kweSpZ
292DeepMoCaP: Deep Optical Motion Capturehttps://bit.ly/30mjTdT
293TrOCR: Transformer-based Optical Character Recognitionhttps://bit.ly/3DqenW5
294Moving Fashionhttps://bit.ly/2YGtjA1
295StyleNeRFhttps://bit.ly/31W4Mbz
296ECA-Net: :Efficient Channel Attentionhttps://bit.ly/3n92i1s
297Inferring High Resolution Traffic Accident risk mapshttps://bit.ly/3HgovD6
298Bias Loss: For Mobile Neural Networkhttps://bit.ly/3qvBPNO
299ByteTrack: Multi-Object Trackinghttps://bit.ly/3c3l7wQ
300Non-Deep Networkhttps://bit.ly/3qwZwoV
301Temporal Attentive Covariancehttps://bit.ly/3ontCbP
302Plan-then-generate: Controlled Data to Text Generationhttps://bit.ly/3DcbsA6
303Dynamic Visual Reasoninghttps://bit.ly/31Q4BhP
304MedMNIST: Medical MNIST Datasethttps://bit.ly/3qxuqxq
305Colossal-AI: A PyTorch-Based Deep Learning System For Large-Scale Parallel Traininghttps://bit.ly/3wG6Xv8
306Recursively Embedded Atom Neural Network(REANN)https://bit.ly/3F1JKqe
307PolyTrack: for fast multi-object tracking and segmentationhttps://bit.ly/3DeBmmS
308Can contrastive learning avoid shortcut solutions?https://bit.ly/3wHJIk9
309ProjectedGAN: To Improve Image Qualityhttps://bit.ly/30hw8Zm
310**Arch-Net: A Family Of Neural Networks Built With Operators To Bridge The Gap **https://bit.ly/3oFOCef
311PP-ShiTu:A Practical Lightweight Image Recognition Systemhttps://bit.ly/3naurFw
312EditGANhttps://bit.ly/30gYd2Z
313Panoptic 3D Scene Segmentationhttps://bit.ly/3caSvla
314PARP: Improve the Efficiency of NNhttps://bit.ly/3DakTjt
315WORD: Organ Segmentation Datasethttps://bit.ly/3qv5OW2
316DenseULearnhttps://bit.ly/3ohRiyi
317Does Thermal data make the detection systems more reliable?https://bit.ly/3sQgTSO
318MADDNESS: Approximate Matrix Multiplication (AMM)https://bit.ly/3zgVIL4
319Deceive D: Adaptive Pseudo Augmentationhttps://bit.ly/3sIG6yA
320OadTRhttps://bit.ly/3JsUHUF
321OnePassImageNethttps://bit.ly/3sKL6Ti
322Image-specific Convolutional Kernel Modulation for Single Image Super-resolutionhttps://bit.ly/3FUpA20
323TransMixhttps://bit.ly/3EH93gH
324PytorchVideohttps://bit.ly/3JvgDP7
325MetNet-2https://bit.ly/3sMZb2M
326Unsupervised deep learning identifies semantic disentanglementhttps://bit.ly/3JyAwVi
327Story Visualizationhttps://bit.ly/3qB554i
328MetaFormerhttps://bit.ly/3sLBebP
329GauGAN2https://bit.ly/3pGrIVH
330SciGAPhttps://bit.ly/3EB7e4U
331Generative Flow Networks (GFlowNets)https://bit.ly/3Jv9YEz
332Ensemble Inversionhttps://bit.ly/3ECwbg9
333SAVihttps://bit.ly/3eF6txe
334Digital Optical Neural Networkhttps://bit.ly/3EI07rh
335Image-Generation Research With Manifold Matching Via Metric Learninghttps://bit.ly/3FUomnq
336GHN-2(Graph HyperNetworks)https://bit.ly/3qzc5yB
337NeatNethttps://bit.ly/3sLY17r
338NeuralProphethttps://bit.ly/3JrUK38
339Background Activation Suppression for Weakly Supervised Object Detectionhttps://bit.ly/3Jvyzt2
340Learning to Detect Every Thing in an Open Worldhttps://bit.ly/3mKxOTc
341PoolFormerhttps://bit.ly/3qFHNtS
342GLIPhttps://bit.ly/3mK3bgx
343PHALPhttps://bit.ly/3eJJvEV
344PixMixhttps://bit.ly/3Hqh77m
345CodeNethttps://bit.ly/32RPx3X
346GANgealinghttps://bit.ly/3EIkO6k
347Semantic Diffusion Guidancehttps://bit.ly/3JsNzI3
348TokenLearnerhttps://bit.ly/3mLG4lM
349Temporal Fusion Transformer (TFT)https://bit.ly/3JuHcno
350HiClass: Evaluation Metrics for Local Hierarchical Classificationhttps://bit.ly/3JHmn8H
351Stable Long Term Recurrent Video Super Resolutionhttps://bit.ly/3qFlPHl
352AdaViThttps://bit.ly/3eDASMj
353Few-Shot Learner (FSL)https://bit.ly/3ELOOym
354Exemplar Transformershttps://bit.ly/3qzJE3C
355StyleSwinhttps://bit.ly/3HqkCe4
356RepMLNethttps://bit.ly/32DxbUu
3572 Stage Unethttps://bit.ly/3JGjIMq
358Untrained Deep NNhttps://bit.ly/3JplL7r
359SeMaskhttps://bit.ly/3zfouM8
360JoJoGANhttps://bit.ly/31gl9Qi
361ELSAhttps://bit.ly/3mLWScb
362PRIMEhttps://bit.ly/3FI14RZ
363GLIDEhttps://bit.ly/31ixB20
364StyleGAN-Vhttps://bit.ly/3Jvx91G
365SLIP: Self-supervision meets Language-Image Pre-traininghttps://bit.ly/3qAjL3r
366SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoshttps://bit.ly/3tYNxlp
367Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Resultshttps://bit.ly/3tZFyEQ
368PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretabilityhttps://bit.ly/3LCKENk
369Vision Transformer with Deformable Attentionhttps://bit.ly/3tY3s3k
370A Transformer-Based Siamese Network for Change Detectionhttps://bit.ly/3DxPYP5
371Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attentionhttps://bit.ly/3qRsTle
372SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detectionhttps://bit.ly/3tXduls
373HyperionSolarNet: Solar Panel Detection from Aerial Imageshttps://bit.ly/35v2rX6
374Realistic Full-Body Anonymization with Surface-Guided GANshttps://bit.ly/3DwBNd4
375Generalized Category Discoveryhttps://bit.ly/3IZ1HaC
376KerGNNs: Interpretable Graph Neural Networks with Graph Kernelshttps://bit.ly/3DtWtlU
377Optimization Planning for 3D ConvNetshttps://bit.ly/3K38e5p
378gDNA: Towards Generative Detailed Neural Avatarshttps://bit.ly/3DEtFHC
379SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapshttps://bit.ly/3NIieTA
380HYDLA: Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learninghttps://bit.ly/379dy8v
381HardBoost: Boosting Zero-Shot Learning with Hard Classeshttps://bit.ly/379diX5
382DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Imageshttps://bit.ly/3Lu0UzU
383Q-ViT: Fully Differentiable Quantization for Vision Transformerhttps://bit.ly/3qXv9Ym
384SPAMs: Structured Implicit Parametric Modelshttps://bit.ly/3iU95cL
385GeoFill: Reference-Based Image Inpainting of Scenes with Complex Geometryhttps://bit.ly/3qUwCP6
386Improving language models by retrieving from trillions of tokenshttps://bit.ly/37aKsG5
387StylEx finds and visualizes disentangled attributes that affect a classifier automatically.https://bit.ly/3qYwYEf
388โ€˜ReLICv2โ€™: Pushing The Limits of Self-Supervised ResNethttps://bit.ly/3JZXy7C
389โ€˜Deticโ€™: A Method to Detect Twenty-Thousand Classes using Image-Level Supervisionhttps://bit.ly/3iRtsqZ
390Momentum Capsule Networkshttps://bit.ly/3NFDv0j
391RelTR: Relation Transformer for Scene Graph Generationhttps://bit.ly/3iVBWgB
392Transformer based SAR Images Despeckinghttps://bit.ly/3qWeILH
393ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentationhttps://bit.ly/3wWGY4T
394VRT: A Video Restoration Transformerhttps://bit.ly/3K44YXw
395You Only Cut Once: Boosting Data Augmentation with a Single Cuthttps://bit.ly/36L8pDW
396StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetshttps://bit.ly/3iRlEp8
397The KFIoU Loss for Rotated Object Detectionhttps://bit.ly/3NHUL5e
398The Met Dataset: Instance Level Recognitionhttps://bit.ly/3K7lPJ2
399Alphacode: a System that can compete at average human levelhttps://bit.ly/3qXIIH5
400Third Time's the Charm? Image and Video Editing with StyleGAN3https://bit.ly/35vAoqx
401NeuralFusion: Online Depth Fusion in Latent Spacehttps://bit.ly/3uFaysA
402VOS: Learning what you don't know by VIRTUAL OUTLIER SYNTHESIShttps://bit.ly/3uPG9rG
403Self-Conditioned Generative Adversarial Networks for Image Editinghttps://bit.ly/3tX8m0u
404TransformNet: Self-supervised representation learning through predicting geometric transformationshttps://bit.ly/3uOCfPM
405YOLOv7 - Framework Beyond Detectionhttps://bit.ly/3wXU81y
406F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantizationhttps://bit.ly/3DzhFXU
407Block-NeRF: Scalable Large Scene Neural View Synthesishttps://bit.ly/3LyELk5
408Patch-NetVLAD+: Learned patch descriptor and weighted matching strategy for place recognitionhttps://bit.ly/375C76y
409COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasetshttps://bit.ly/3NCK6bZ
410ScoreNet: Learning Non-Uniform Attention and Augmentation for Transformer-Based Histopathological Image Classificationhttps://bit.ly/3uJuMBz
411Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugeshttps://bit.ly/388imeT
412How Do Vision Transformers Work?https://bit.ly/3NE1mO2
413Mirror-Yolo: An attention-based instance segmentation and detection model for mirrorshttps://bit.ly/3LBS96P
414PENCIL: Deep Learning with Noisy Labelshttps://bit.ly/3iXvHc4
415VLP: A Survey on Vision-Language Pre-traininghttps://bit.ly/3J0v2RZ
416Visual Attention Networkhttps://bit.ly/3Dt7rbv
417GroupViT: Semantic Segmentation Emerges from Text Supervisionhttps://bit.ly/3NQv7eG
418Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesishttps://bit.ly/373xs4T
419End to End Cascaded Image De-raining and Object Detetion NNhttps://bit.ly/375PLGw
420Level-K to Nash Equilibriumhttps://bit.ly/3NFRX8t
421Machine Learning for Mechanical Ventilation Controlhttps://bit.ly/3JZCMEV
422The effect of fatigue on the performance of online writer recognitionhttps://bit.ly/3wXSSLS
423State-of-the-Art in the Architecture, Methods and Applications of StyleGANhttps://bit.ly/3iRjl5s
424Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generationhttps://bit.ly/3v5XZXR
425Self-supervised Transformer for Deepfake Detectionhttps://bit.ly/3tXtUdk
426CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Sizehttps://bit.ly/3LxkrQa
427TCTrack: Temporal Contexts for Aerial Trackinghttps://bit.ly/3uM5O4B
428LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Predictionhttps://bit.ly/3uOfKe0
429HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpeninghttps://bit.ly/35tRV2j
430ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretizationhttps://bit.ly/3LwoMmy
431MLSeg: Image and Video Segmentationhttps://bit.ly/38p9iCN
432Image Steganography based on Style Transferhttps://bit.ly/3DJHLaN
433GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grainshttps://bit.ly/3JYPrIg
434AGCN: Augmented Graph Convolutional Networkhttps://bit.ly/3DwZrWN
435StyleBabel: Artistic Style Tagging and Captioninghttps://bit.ly/3j1Klit
436ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRIhttps://bit.ly/38maN4z
437InsetGAN for Full-Body Image Generationhttps://bit.ly/3Dsu9At
438Implicit Feature Decoupling with Depthwise Quantizationhttps://bit.ly/3K1mxaA
439Bamboo: Building Mega-Scale Vision Datasethttps://bit.ly/3wVPalD
440TensoRF: Tensorial Radiance Fieldshttps://bit.ly/3iWAFWI
441FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognitionhttps://bit.ly/3NCHTxd
442One-Shot Adaptation of GAN in Just One CLIPhttps://bit.ly/36NOPab
443SHREC 2021: Classification in cryo-electron tomogramshttps://bit.ly/3iSXpqv
444MaskGIT: Masked Generative Image Transformerhttps://bit.ly/3qSQz8I
445Detection, Recognition, and Tracking: A Surveyhttps://bit.ly/378G8qw
446Mixed Differential Privacyhttps://bit.ly/3IZ0MGU
447Mixed DualStyleGANhttps://bit.ly/3wTyAmD
448BigDetectionhttps://bit.ly/3DuZSRk
449Feature visualization for convolutional neural networkhttps://bit.ly/3Dwf6FJ
450AutoAvatarhttps://bit.ly/38m9ClF
451A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstructionhttps://bit.ly/3Dz1idF
452StyleT2Ihttps://bit.ly/35u5Wx0
453L^3U-nethttps://bit.ly/3iTOq8r
454Balanced MSEhttps://bit.ly/3rxt7yo
455BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformershttps://bit.ly/36m3HfC
456TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editinghttps://bit.ly/3JQKZKS
457On the Importance of Asymmetry for Siamese Representation Learninghttps://bit.ly/3JNgcyt
458On One-Class Graph Neural Networks for Anomaly Detection in Attributed Networkshttps://bit.ly/3uQTC3P
459Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depthhttps://bit.ly/3KWT6a4
460Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detectionhttps://bit.ly/3L8a59H
461DaViT: Dual Attention Vision Transformershttps://bit.ly/3Engc7e
462SPAct: Self-supervised Privacy Preservation for Action Recognitionhttps://bit.ly/3KTNvRW
463Class-Incremental Learning with Strong Pre-trained Modelshttps://bit.ly/3MdlcOq
464RBGNet: Ray-based Grouping for 3D Object Detection by Center for Data Sciencehttps://bit.ly/3EqkydH
465Event Transformerhttps://bit.ly/3KUsMxc
466ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehensionhttps://bit.ly/3M6RgDE
467A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Researchhttps://bit.ly/3xAyqRj
468Simple Baselines for Image Restorationhttps://bit.ly/3vt4tjB
469Masked Siamese Networks for Label-Efficient Learninghttps://bit.ly/3viEs6s
470Neighborhood Attention Transformerhttps://bit.ly/3jNExK3
471TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentationhttps://bit.ly/3M3EA0K
472MVSTER: Epipolar Transformer for Efficient Multi-View Stereohttps://bit.ly/3MaDTCR
473Temporally Efficient Vision Transformer for Video Instance Segmentationhttps://bit.ly/3w6xkf3
474EditGAN: High-Precision Semantic Image Editinghttps://bit.ly/3yx2JJ2
475CenterNet++ for Object Detectionhttps://bit.ly/3woxrBG
476A case for using rotation invariant features in state of the art feature matchershttps://bit.ly/3kZ1x9A
477WebFace260M: A Benchmark for Million-Scale Deep Face Recognitionhttps://bit.ly/3w2T3Vd
478JIFF: Jointly-aligned Implicit Face Function for High-Quality Single View Clothed Human Reconstructionhttps://bit.ly/3N9Me9U
479Image Data Augmentation for Deep Learning: A Surveyhttps://bit.ly/3PfC1uA
480StyleGAN-Human: A Data-Centric Odyssey of Human Generationhttps://bit.ly/3PqV710
481Few-shot Head Swapping In The Wild Secrets Revealed By Department Of Computer Vision Technology (vis)https://bit.ly/3w7xm6c
482CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIPhttps://bit.ly/3N3cEKu
483HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelinghttps://bit.ly/3Nqnevx
484Generative Adversarial Networks for Image Super-Resolution: A Surveyhttps://bit.ly/39jyL0U
485CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classificationhttps://bit.ly/3N7Qd6V
486C3-STISR: Scene Text Image Super-resolution with Triple Clueshttps://bit.ly/3l1352C
487Barbershop: GAN-based Image Compositing using Segmentation Maskshttps://bit.ly/39hus6d
488DANBO: Disentangled Articulated Neural Body Representationshttps://bit.ly/3LkqWp3
489BlobGAN: Spatially Disentangled Scene Representationshttps://bit.ly/3sufEYz
490Text to artistic image generationhttps://bit.ly/3w6wzmd
491Sequencer: Deep LSTM for Image Classificationhttps://bit.ly/3sulPvT
492IVY: An Open-Source Tool To Make Deep Learning Code Compatible Across Frameworkshttps://bit.ly/3M6MbvJ
493Introspective Deep Metric Learninghttps://bit.ly/3w2pZ02
494KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointshttps://bit.ly/3wnRhwF
495GraphWorld: A Methodology For Analyzing The Performance Of GNN Architectures On Millions Of Synthetic Benchmark Datasetshttps://bit.ly/3PUQexk
496Group R-CNN for Weakly Semi-supervised Object Detection with Pointshttps://bit.ly/3zfvU3W
497Few-Shot Head Swapping in the Wildhttps://bit.ly/3xapGkn
498StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-maphttps://bit.ly/3GKX4Bi
499Spiking Approximations of the MaxPooling Operation in Deep SNNshttps://bit.ly/3GLp7AG
500Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationhttps://bit.ly/3NTGsJQ

Thanks for Reading๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰