event
PhD Defense by Pramod Chunduri
Primary tabs
Title: Enabling Semantically Richer Queries over Unstructured Data
Pramod Chunduri
Ph.D. Candidate
School of Computer Science
College of Computing
Georgia Institute of Technology
Date: Wednesday, July 23, 2025
Time: 2:00 PM - 4:00 PM ET
Location: Klaus 3100
Online: Microsoft Teams
Committee:
Dr. Joy Arulraj (advisor), School of Computer Science, Georgia Institute of Technology
Dr. Kexin Rong, School of Computer Science, Georgia Institute of Technology
Dr. Xu Chu, School of Computer Science, Georgia Institute of Technology
Dr. Shamkant Navathe, School of Computer Science, Georgia Institute of Technology
Dr. Ali Payani, Cisco Research
Abstract:
Querying unstructured data such as video, audio, text is critical for domains ranging from traffic surveillance to healthcare and finance. Modern AI models (e.g., vision and language models) unlock significant potential for extracting fine-grained information from unstructured data. However, existing data systems that leverage these models primarily focus on efficiently executing semantically simple queries.
This thesis argues that enabling semantically rich queries over unstructured data requires rethinking both the query execution strategies and the query interfaces. To this end, we introduce three systems designed to support the efficient and accurate processing of semantically rich queries over unstructured data.
First, we present Zeus, a video analytics system that efficiently localizes complex actions in videos using a reinforcement learning (RL)-based query executor. By using accuracy-based rewards during query planning, Zeus significantly improves efficiency while meeting user-specified accuracy targets.
Next, we introduce SketchQL, a visual query interface that allows users to sketch complex video moments. SketchQL maps these sketches to fine-grained video moments using a transformer model trained on synthetically generated data. SketchQL significantly enhances the usability and accuracy of fine-grained video moment retrieval.
Finally, we present Halo, a long-context question answering (QA) framework designed for domain-augmented queries. Halo incorporates domain knowledge into the QA pipeline via a Domain Hints interface, allowing users to specify structured suggestions that augment the original query. A three-stage execution pipeline then applies these hints automatically and optimally, improving both the efficiency and accuracy of long-context QA.
Groups
Status
- Workflow Status:Published
- Created By:Tatianna Richardson
- Created:07/14/2025
- Modified By:Tatianna Richardson
- Modified:07/14/2025
Categories
Keywords
Target Audience