Skip to content

Add Group V project card #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Nawfal-AI wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Add Group V project card #1

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
03ce9f8
Add Group V project card
Nawfal-AI May 30, 2026
6d0721a
Add Group V teaser image
Nawfal-AI May 30, 2026
d33f9d5
reordered cards
nihermann Jun 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
67 changes: 21 additions & 46 deletions index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,51 +301,6 @@ <h3>Open-Vocabulary Object Tracking with Grounding DINO, SAM 2 and CLIP</h3>
</div>
</article>














































<article class="project-card">
<div class="teaser" role="img" aria-label="Image retrieval with CLIP.">
<img src="assets/group_Q.png" alt="Image retrieval preview" style="position:absolute; inset:0; width:100%; height:100%; object-fit:cover; z-index:2;">
Expand Down Expand Up @@ -435,7 +390,27 @@ <h3>From Raw Footage to Recipe: Extracting Cooking Steps from Egocentric Video</
</label>
</div>
</article>


<article class="project-card">
<div class="teaser" role="img" aria-label="AI image captioning system turning video frames into short action labels.">
<img src="assets/group_V.png" alt="Group V image captioning preview" style="position:absolute; inset:0; width:100%; height:100%; object-fit:cover; z-index:2;">
<span class="teaser-label" style="z-index:3;">Group V</span>
</div>
<div class="project-content">
<p class="project-meta">Video understanding, vision-language models, action captioning</p>
<h3>Action/Event-Focused Captioning: A Three-Model Comparison</h3>
<p class="project-abstract">
This project explores how pretrained image-captioning models can be adapted to produce short action-focused captions for video activity timelines. Instead of generating long descriptive captions, we fine-tune BLIP, ViT-GPT2, and Microsoft GIT on COCO action captions so that the models output compact labels such as “person walking” or “coffee being poured.”
<br><br>
For video inference, frames are sampled over time, captioned by the fine-tuned models, and de-duplicated into a simple activity timeline. The project compares original and fine-tuned models using BLEU-1, BLEU-2, METEOR, and ROUGE-L, and analyzes whether architecture choice still matters after all models are adapted to the same action-caption task.
</p>
<label class="project-toggle-label">
<input class="project-toggle" type="checkbox" aria-label="Toggle full project pitch">
<span class="project-toggle-more">Read more</span>
<span class="project-toggle-less">Show less</span>
</label>
</div>
</article>


<article class="project-card add-project-card">
Expand Down