arxiv:2407.00830
Fatih C. Akyon
fcakyon
AI & ML interests
multi-modal learning, video understanding
Organizations
spaces
7
pinned
Runtime error
52
π₯
Zero Shot Video Classification
pinned
Runtime error
39
π½
Video Classification
pinned
Running
12
π₯
YOLOv8 Segmentation
Running
22
π
Small Object Detection with YOLOX
Running
12
πΌοΈ
Streamlit Image Comparison
Runtime error
3
π₯
Timesformer Video Classification
models
15
fcakyon/test-model
Image Segmentation
β’
Updated
β’
11
fcakyon/yolov5n-cls-v7.0
Image Classification
β’
Updated
β’
11
β’
2
fcakyon/yolov5n-seg-v7.0
Updated
β’
5
fcakyon/yolov5n-v7.0
Object Detection
β’
Updated
β’
926
β’
2
fcakyon/yolov5s-v7.0
Object Detection
β’
Updated
β’
1.19k
β’
13
fcakyon/timesformer-large-finetuned-k600
Video Classification
β’
Updated
β’
1
β’
1
fcakyon/timesformer-large-finetuned-k400
Video Classification
β’
Updated
β’
2
fcakyon/timesformer-large-finetuned-ssv2
Video Classification
β’
Updated
β’
52
fcakyon/timesformer-hr-finetuned-k600
Video Classification
β’
Updated
β’
1
fcakyon/timesformer-base-finetuned-ssv2
Video Classification
β’
Updated
β’
4