Boundary Captioning
4 papers with code • 1 benchmarks • 2 datasets
Provided with the timestamp of a boundary inside a video, the machine is required to generate sentences describing the status change at the boundary.
Benchmarks
These leaderboards are used to track progress in Boundary Captioning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Kinetics
Kinetics-GEB+
Most implemented papers
GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval
showlab/geb-plus
•
•
In this paper, we introduce a new dataset called Kinetic-GEB+.
Exploiting Context Information for Generic Event Boundary Captioning
Previous methods only process the information of a single boundary at a time, which lacks utilization of video context information.
Dual-Stream Transformer for Generic Event Boundary Captioning
gx77/dual-stream-transformer-for-generic-event-boundary-captioning
•
•
This paper describes our champion solution for the CVPR2022 Generic Event Boundary Captioning (GEBC) competition.
LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning
This paper proposes an effective model LLMVA-GEBC (Large Language Model with Video Adapter for Generic Event Boundary Captioning): (1) We utilize a pretrained LLM for generating human-like captions with high quality.
