Bhalaji Nagarajan
bhalajin
·
AI & ML interests
None yet
Recent Activity
posted an update 3 days ago
###### CVPR2026 MetaFood Workshop Challenge Alert ######
🍽️ Dishcovery: Mission II VLM Challenge
We’re excited to share that the Dishcovery II Vision-Language Model Challenge is LIVE, as part of the 3rd MetaFood Workshop @ CVPR 2026.
👉 Join the challenge:
https://www.kaggle.com/competitions/dishcovery-mission-ii-cvpr-2026
👉 Dataset collection (Hugging Face):
https://huggingface.co/datasets/jesusmolrdv/MTF25-VLM-Challenge-Dataset-Web
https://huggingface.co/datasets/jesusmolrdv/MTF25-VLM-Challenge-Dataset-Synth
👉 Workshop details:
https://sites.google.com/view/cvpr-metafood-2026
🔍 Task
Build a Vision-Language Model that aligns food images with text under real-world conditions:
1. Multi-label retrieval → identify relevant ingredients/components
2. Single-label retrieval → select the best dense food description
📦 Dataset Highlights
- 400K+ image–caption pairs
- Mix of real, noisy, and synthetic data
- Designed for fine-grained food understanding
- Reflects real-world multimodal challenges
⚔️ What makes this interesting?
- Not just accuracy → efficiency matters
- Robustness to noise and domain shift
- Fine-grained alignment between visual and semantic concepts
- Benchmark for next-gen VLMs (CLIP, SigLIP, LLaVA-style models)
📅 Timeline (key milestones)
May 1, 2026 → Final predictions + method summary
🚀 Why participate?
- Benchmark your models on large-scale multimodal food data
- Test robustness under realistic conditions
- Gain visibility via a global leaderboard
- Contribute to the growing Food × Vision × Language research space
🍳 The kitchen is heating up — looking forward to seeing what the community builds!
#multimodal #computervision #vlm #deeplearning #datasets #kaggle #huggingface #ai #research
Dataset Citation: https://huggingface.co/papers/2407.03463 posted an update 11 months ago
###### CVPR2025 Workshop Challenge Alert ######
🫠 Between deadlines, rebuttals, and existential crises??? "We got you!!!!"
📢 Our new CVPR25 multi-modal challenge is online !!!
🍽️ Dishcovery: VLM MetaFood Challenge!!!! 🍽️
😋🧫 Can your groundbreaking VLM understand the difference between sushi styles, pasta types, or cooking methods from just image + caption pairs?
🌐 Our Task: Match fine-grained images to food descriptions
Challenge Highlights:
📦 400K food image-caption pairs, a little taste to get you started !!!
🔬 Got a SoTA VLM? Come test it on our challenging test sets !!!
🎯 Challenge for everyone! Easy to use SigLIP baseline is provided !!!
🔍 Real, synthetic, noisy data – just like real life - Will your VLM redefine how people track their diets??? ( 🗣️ We believe so!!! )
🔗 Join the challenge: https://www.kaggle.com/competitions/dishcovery-vlm-mtf-cvpr-2025
🗓️ Deadline: Phase I: 4th of May, 2025 - Phase II: 10th of May, 2025
👉 Workshop website: https://sites.google.com/view/cvpr-metafood-2025
#CVPR25 #ComputerVision #CV #Deeplearning #DL #VisionLanguage #VLM #multimodal #FoundationModels authored a paper over 2 years ago
All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and
Redundancy ReductionOrganizations
