SIDDHI VINAYAK, HATTINGADI (KAR)
#bharatmandir

Hattiangadi was once Alupa capital and the shrine is believed to be of around 7th-8th c.
Ganesha vigrah is about 2.5 feet tall, carved out of Shaligram stone. It is the only Ganesha murti where His curly black hair is left loose.

This was the place of meditation of Sri Govindarama Yathivarya. He had predicted that the shrine would attain fame in next 300 years.
Ganesha is believed to grow in size each year and since it is believed that he grants all wishes so the title of Siddhi is conferred on Him.
The offering of singara (areca nut flower) is considered extremely sacred here.
If the flower falls from Ganesha’s crown during aarti, it signifies that wish will be fulfilled.
Sahasra Narikela Ganayaga (pooja with 1008 coconuts) is another special prayer conducted.

More from Jaya_Upadhyaya

More from All

How can we use language supervision to learn better visual representations for robotics?

Introducing Voltron: Language-Driven Representation Learning for Robotics!

Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z

🧵👇(1 / 12)


Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.

Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)

The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (
https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).

The secret is *balance* (3/12)

Starting with a masked autoencoder over frames from these video clips, make a choice:

1) Condition on language and improve our ability to reconstruct the scene.

2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)

By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.

Why is the ability to shape this balance important? (5/12)

You May Also Like