pritamqu / crisscross

[AAAI 2023 (Oral)] CrissCross: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity

• 👋 Hi, I’m Pritam, please check my website for more information www.pritamsarkar.com
• 👀 I’m interested in machine learning 🧠, photography 📷, and film making 🎞️ .
• 💞️ I’m always open to coffee and discuss research.
• 📫 reach me: pritam[dot]sarkar[at]queensu[dot]ca.

crisscross's Issues

Category list for Kinetics-Sound dataset

Hi, I am planning to do research based on your model. I found that in the paper that you cited (Look, listen and
learn), there are 34 classes in Kinetics-Sound. Among these classes, 32 classes are used in your research. Could you provide the category list? Many thanks for considering my request.

upload the all code

Hello!
I am really interested in your work by studying your paper.
When will you upload the all code?

Could I ask when training code is released?

Hello, I am planning to do research based on this model. Could you release the entire code..? Would it be available within this month? Thank you in advance.

upload training code

May I ask when will you upload training code?

About training and testing dataset

Hi Pritam, thank you very much for your amazing work. I have some questions about the dataset you used in this work. The pretrained dataset : K400, AudioSet and Kinetics-Sound, do you always use both audio and visual information, and do they always contain audio stream? Because I am trying k400, but I found some videos miss audio stream. In addition, the downstream dataset like UCF-101 and HMDB-51, do you use both audio and visual pairs , or just use visual information for evaluation? It seems that videos files in UCF-101 do not always contain the audio stream. Thank you very much.