Search Results for author:
Found 7 papers, 1 papers with code
M-LLM Based Video Frame Selection for Efficient Video Understanding
Empirical results show that the proposed M-LLM video frame selector improves the performances various downstream video Large Language Model (video-LLM) across medium (ActivityNet, NExT-QA) and long (EgoSchema, LongVideoBench) context video question answering benchmarks.
Multimodal Instruction Tuning with Hybrid State Space Models
Remarkably, our model enhances inference efficiency for high-resolution images and high-frame-rate videos by about 4 times compared to current models, with efficiency gains increasing as image resolution or video frames rise.
Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
We demonstrate that our approach: (a) significantly improves the quality of 3-D reconstruction for our small-parallax setting, (b) does not cause any degradation for data with large-parallax, and (c) maintains the generalizability and scalability of geometry-based sparse SfM.
Movies2Scenes: Using Movie Metadata to Learn Scene Representation
However, labeling individual scenes is a time-consuming process.
Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
To assess the effectiveness of ShotCoL on novel applications of scene boundary detection, we take on the problem of finding timestamps in movies and TV episodes where video-ads can be inserted while offering a minimally disruptive viewing experience.
A Robust and Efficient Framework for Sports-Field Registration
We propose a novel framework to register sports-fields as they appear in broadcast sports videos.
Cross-view Action Modeling, Learning and Recognition
We present a novel multiview spatio-temporal AND-OR graph (MST-AOG) representation for cross-view action recognition, i. e., the recognition is performed on the video from an unknown and unseen view.
