microsoft/XPretrain issues and pull requests

#44 - Details of zero-shot performance on SSv2

Issue - State: open - Opened by bpiyush about 2 months ago

#44 - Details of zero-shot performance on SSv2

Issue - State: open - Opened by bpiyush about 2 months ago

#43 - about clipvip-vit-16 pretrained weights file

Issue - State: open - Opened by musicman217 5 months ago

#43 - about clipvip-vit-16 pretrained weights file

Issue - State: open - Opened by musicman217 5 months ago

#42 - Pretrained Checkpoints of CLIP-VIP

Issue - State: open - Opened by hardlipay 5 months ago

#42 - Pretrained Checkpoints of CLIP-VIP

Issue - State: open - Opened by hardlipay 5 months ago

#41 - About activitynet captions dataset in CLIP-ViP

Issue - State: open - Opened by musicman217 5 months ago

#41 - About activitynet captions dataset in CLIP-ViP

Issue - State: open - Opened by musicman217 5 months ago

#40 - Is there no classification in the HD-VILA dataset?

Issue - State: open - Opened by shuangtianjiuyou 5 months ago - 1 comment

#40 - Is there no classification in the HD-VILA dataset?

Issue - State: open - Opened by shuangtianjiuyou 5 months ago - 1 comment

#39 - Pretrained Checkpoints of LF-VILA

Issue - State: closed - Opened by pilibb0712 6 months ago - 1 comment

#39 - Pretrained Checkpoints of LF-VILA

Issue - State: closed - Opened by pilibb0712 6 months ago - 1 comment

#38 - Hi, how to understand the LF-hdvila-8m?

Issue - State: open - Opened by sunwhw 8 months ago - 1 comment

#38 - Hi, how to understand the LF-hdvila-8m?

Issue - State: open - Opened by sunwhw 8 months ago - 1 comment

#37 - Dockerfile and requirements for Clip-ViP

Issue - State: open - Opened by ncTimTang 8 months ago

#37 - Dockerfile and requirements for Clip-ViP

Issue - State: open - Opened by ncTimTang 8 months ago

#36 - About LF-VILA code in PatchEmbed3D of video encoder

Issue - State: open - Opened by musicman217 8 months ago

#36 - About LF-VILA code in PatchEmbed3D of video encoder

Issue - State: open - Opened by musicman217 8 months ago

#35 - Update Dockerfile for Issue #34

Pull Request - State: open - Opened by MasoudKaviani 9 months ago

#35 - Update Dockerfile for Issue #34

Pull Request - State: open - Opened by MasoudKaviani 9 months ago

#34 - Error on starting horovod

Issue - State: open - Opened by MasoudKaviani 9 months ago

#34 - Error on starting horovod

Issue - State: open - Opened by MasoudKaviani 9 months ago

#33 - Bump transformers from 4.30.0 to 4.36.0 in /LF-VILA/docker

Pull Request - State: open - Opened by dependabot[bot] 11 months ago
Labels: dependencies

#33 - Bump transformers from 4.30.0 to 4.36.0 in /LF-VILA/docker

Pull Request - State: open - Opened by dependabot[bot] 11 months ago
Labels: dependencies

#32 - Code for transcript text processing

Issue - State: open - Opened by wwyy1234 about 1 year ago - 1 comment

#32 - Code for transcript text processing

Issue - State: open - Opened by wwyy1234 about 1 year ago - 1 comment

#31 - Model checkpoints

Issue - State: open - Opened by michaeltian108 about 1 year ago

#31 - Model checkpoints

Issue - State: open - Opened by michaeltian108 about 1 year ago

#30 - Error in finetuning

Issue - State: open - Opened by Ravindu-Yasas-Nagasinghe about 1 year ago - 1 comment

#30 - Error in finetuning

Issue - State: open - Opened by Ravindu-Yasas-Nagasinghe about 1 year ago - 1 comment

#29 - video caption of HD-VILA-100M Dataset

Issue - State: closed - Opened by zyyyz about 1 year ago - 1 comment

#28 - Code improvements

Pull Request - State: open - Opened by tosemml over 1 year ago - 2 comments

#27 - How long does CLIP-VIP pretraining takes?

Issue - State: open - Opened by daizuozhuo over 1 year ago - 1 comment

#26 - About the zero-shot performance

Issue - State: closed - Opened by LiuRicky over 1 year ago - 1 comment

#25 - where are the train9k.jsonl and test1ka.jsonl files in MSRVTT retrieval?

Issue - State: closed - Opened by wangpichao over 1 year ago - 3 comments

#24 - Asking for a simple script to get text and video features

Issue - State: open - Opened by yotammarton over 1 year ago - 8 comments

#23 - Bump transformers from 4.15.0 to 4.30.0 in /LF-VILA/docker

Pull Request - State: closed - Opened by dependabot[bot] over 1 year ago
Labels: dependencies

#22 - CLIP-VIP OFA caption generate

Issue - State: closed - Opened by tikboaHIT over 1 year ago - 1 comment

#21 - MSR-VTT fine tune epochs number

Issue - State: closed - Opened by ffnc1020 over 1 year ago - 2 comments

#20 - Captions for HD-ViLA-100M

Issue - State: closed - Opened by hanoonaR over 1 year ago - 1 comment

#19 - Ways to open the .mdb caption files

Issue - State: closed - Opened by ffnc1020 over 1 year ago - 2 comments

#18 - How to prepare pretrain data for LF-VILA?

Issue - State: closed - Opened by yliu-cs over 1 year ago - 2 comments

#17 - Video compression/decoding methods of each dataset in CLIP-ViP

Issue - State: closed - Opened by fadzaka12 over 1 year ago - 1 comment

#16 - Question regarding video proxy mechanism in CLIP-ViP

Issue - State: closed - Opened by fadzaka12 over 1 year ago - 4 comments

#15 - About the zero-shot performance

Issue - State: closed - Opened by LiuRicky over 1 year ago - 2 comments

#14 - About OFA-Caption generated captions on HD-VILA-100M

Issue - State: closed - Opened by LiuRicky over 1 year ago - 1 comment

#13 - Reproducing the result of CLIP-ViP performance on MSRVTT

Issue - State: closed - Opened by justopit over 1 year ago - 4 comments

#12 - How to use HD-VILA as multimodal TextEncoder?

Issue - State: closed - Opened by Celia0u0 over 1 year ago - 3 comments

#11 - Where is the MSRVTT json file in CLIP-ViP?

Issue - State: closed - Opened by justopit over 1 year ago - 2 comments

#10 - In CLIP-ViP, what is the results of OFA captions + HD-VILA-10M?

Issue - State: closed - Opened by SCZwangxiao over 1 year ago - 1 comment

#9 - [CLS] token in CLIP-ViP

Issue - State: closed - Opened by goonbamm almost 2 years ago - 2 comments

#8 - Long Video Processing in LF-VILA

Issue - State: closed - Opened by vateye almost 2 years ago - 3 comments

#7 - Where can i get the asr text

Issue - State: closed - Opened by Satan012 almost 2 years ago - 1 comment

#6 - Code for transcript text processing

Issue - State: closed - Opened by RyanMarten about 2 years ago - 27 comments

#5 - releasing code and pretrain

Issue - State: closed - Opened by maralzar about 2 years ago - 3 comments

#4 - where to download the ASR transcriptions?

Issue - State: closed - Opened by TXH-mercury over 2 years ago - 1 comment

#3 - Questions about HD-VILA

Issue - State: closed - Opened by HenryHZY over 2 years ago - 4 comments

#2 - HD-VILA-100M dataset, where is the text corresponding to each video?

Issue - State: closed - Opened by Qiliqing over 2 years ago - 2 comments

#1 - Update README.md

Pull Request - State: closed - Opened by TiankaiHang over 2 years ago

GitHub / microsoft/XPretrain issues and pull requests