Douglas Gray
@de3ug.bsky.social
Visual Search @amazon. Here for computer vision, ML, NLP research discussion, but may drift into hobbies like astrophotography.
https://de3ug.github.io
https://de3ug.github.io
🔗 Links
Website 🌐 mrr-workshop.github.io
Submit ✍️ openreview.net/group?id=the...
RT, tag a colleague, and see you in Hawai‘i! 🤙 #CFP #MultimodalAI #Retrieval
Website 🌐 mrr-workshop.github.io
Submit ✍️ openreview.net/group?id=the...
RT, tag a colleague, and see you in Hawai‘i! 🤙 #CFP #MultimodalAI #Retrieval
Multimodal Representation and Retrieval [MRR 2025]
A workshop on multimodal representation and retrieval at ICCV 2025, focusing on multimodal data in applications like e-commerce, social media, and short videos.
mrr-workshop.github.io
May 12, 2025 at 10:56 PM
🔗 Links
Website 🌐 mrr-workshop.github.io
Submit ✍️ openreview.net/group?id=the...
RT, tag a colleague, and see you in Hawai‘i! 🤙 #CFP #MultimodalAI #Retrieval
Website 🌐 mrr-workshop.github.io
Submit ✍️ openreview.net/group?id=the...
RT, tag a colleague, and see you in Hawai‘i! 🤙 #CFP #MultimodalAI #Retrieval
📆 Timeline
• Submission deadline: 3 Jun 2025 (AoE)
• Notification: 25 Jun 2025
• Workshop: half-day, 19 or 20 Oct 2025 (TBA) during ICCV week, Honolulu
• Submission deadline: 3 Jun 2025 (AoE)
• Notification: 25 Jun 2025
• Workshop: half-day, 19 or 20 Oct 2025 (TBA) during ICCV week, Honolulu
May 12, 2025 at 10:56 PM
📆 Timeline
• Submission deadline: 3 Jun 2025 (AoE)
• Notification: 25 Jun 2025
• Workshop: half-day, 19 or 20 Oct 2025 (TBA) during ICCV week, Honolulu
• Submission deadline: 3 Jun 2025 (AoE)
• Notification: 25 Jun 2025
• Workshop: half-day, 19 or 20 Oct 2025 (TBA) during ICCV week, Honolulu
📝 What counts as multimodal?
Text ↔ image, video, audio, 3-D or sensor data in either the query or the index—for example:
• Image + caption product search
• Audio question ↔ video answer retrieval
• Language queries over robot-sensor logs
Send us 4–8-page papers!
Text ↔ image, video, audio, 3-D or sensor data in either the query or the index—for example:
• Image + caption product search
• Audio question ↔ video answer retrieval
• Language queries over robot-sensor logs
Send us 4–8-page papers!
May 12, 2025 at 10:56 PM
📝 What counts as multimodal?
Text ↔ image, video, audio, 3-D or sensor data in either the query or the index—for example:
• Image + caption product search
• Audio question ↔ video answer retrieval
• Language queries over robot-sensor logs
Send us 4–8-page papers!
Text ↔ image, video, audio, 3-D or sensor data in either the query or the index—for example:
• Image + caption product search
• Audio question ↔ video answer retrieval
• Language queries over robot-sensor logs
Send us 4–8-page papers!
👥 Keynotes:
Chirag Shah (UW)
&
Jianwei Yang (MSR)🎤 Half-day workshop with invited talks + interactive panel—meet the world’s leading vision-&-language researchers, retrieval engineers, and GenAI practitioners.
Chirag Shah (UW)
&
Jianwei Yang (MSR)🎤 Half-day workshop with invited talks + interactive panel—meet the world’s leading vision-&-language researchers, retrieval engineers, and GenAI practitioners.
May 12, 2025 at 10:56 PM
👥 Keynotes:
Chirag Shah (UW)
&
Jianwei Yang (MSR)🎤 Half-day workshop with invited talks + interactive panel—meet the world’s leading vision-&-language researchers, retrieval engineers, and GenAI practitioners.
Chirag Shah (UW)
&
Jianwei Yang (MSR)🎤 Half-day workshop with invited talks + interactive panel—meet the world’s leading vision-&-language researchers, retrieval engineers, and GenAI practitioners.