Ziyang Wang commited on
Commit
9cf02ac
Β·
1 Parent(s): 0385d22

update GitHub URL to Ziyang412/EgoMemReason

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ hf_oauth: true
17
  Live leaderboard for the **EgoMemReason** benchmark: 500 multiple-choice questions over week-long egocentric video, evaluating entity / event / behavior memory.
18
 
19
  - πŸ“„ Paper: *coming soon*
20
- - πŸ’» Reference eval scripts: <https://github.com/Ted412/EgoMemReason>
21
  - πŸ“¦ Public questions: <https://huggingface.co/datasets/Ted412/EgoMemReason>
22
  - 🎬 Source frames: <https://egolife-ai.github.io/>
23
 
 
17
  Live leaderboard for the **EgoMemReason** benchmark: 500 multiple-choice questions over week-long egocentric video, evaluating entity / event / behavior memory.
18
 
19
  - πŸ“„ Paper: *coming soon*
20
+ - πŸ’» Reference eval scripts: <https://github.com/Ziyang412/EgoMemReason>
21
  - πŸ“¦ Public questions: <https://huggingface.co/datasets/Ted412/EgoMemReason>
22
  - 🎬 Source frames: <https://egolife-ai.github.io/>
23
 
SUBMISSION_FORMAT.md CHANGED
@@ -30,7 +30,7 @@ A submission is a single JSON file (`.json`) containing a top-level array of 500
30
 
31
  ## Converting from existing eval-script output
32
 
33
- The reference inference scripts in the [EgoMemReason GitHub repo](https://github.com/Ted412/EgoMemReason) write a list of records with a `pred` field. One-liner to convert:
34
 
35
  ```python
36
  import json
 
30
 
31
  ## Converting from existing eval-script output
32
 
33
+ The reference inference scripts in the [EgoMemReason GitHub repo](https://github.com/Ziyang412/EgoMemReason) write a list of records with a `pred` field. One-liner to convert:
34
 
35
  ```python
36
  import json
app.py CHANGED
@@ -223,7 +223,7 @@ strongest model in the paper reaches **39.6% Overall**.
223
  ### Resources
224
 
225
  - πŸ“„ Paper: *coming soon*
226
- - πŸ’» Code & reference eval scripts: <https://github.com/Ted412/EgoMemReason>
227
  - πŸ“¦ Public questions (no answers): <https://huggingface.co/datasets/Ted412/EgoMemReason>
228
  - 🎬 EgoLife video frames: <https://egolife-ai.github.io/>
229
 
@@ -240,7 +240,7 @@ Upload a JSON file with 500 entries:
240
 
241
  Questions have 4-10 options (letters A-J) β€” `predicted_answer` must be a letter
242
  that appears in that question's `options` dict. See
243
- [SUBMISSION_FORMAT.md](https://github.com/Ted412/EgoMemReason/blob/main/SUBMISSION_FORMAT.md)
244
  for the full spec.
245
 
246
  ### License
 
223
  ### Resources
224
 
225
  - πŸ“„ Paper: *coming soon*
226
+ - πŸ’» Code & reference eval scripts: <https://github.com/Ziyang412/EgoMemReason>
227
  - πŸ“¦ Public questions (no answers): <https://huggingface.co/datasets/Ted412/EgoMemReason>
228
  - 🎬 EgoLife video frames: <https://egolife-ai.github.io/>
229
 
 
240
 
241
  Questions have 4-10 options (letters A-J) β€” `predicted_answer` must be a letter
242
  that appears in that question's `options` dict. See
243
+ [SUBMISSION_FORMAT.md](https://github.com/Ziyang412/EgoMemReason/blob/main/SUBMISSION_FORMAT.md)
244
  for the full spec.
245
 
246
  ### License
scripts/seed_paper_baselines.py CHANGED
@@ -74,7 +74,7 @@ PAPER_TABLE = [
74
  34.0, 42.0, 31.0, 27.0, 38.0, 34.0, 34.0),
75
  ]
76
 
77
- PROJECT_URL = "https://github.com/Ted412/EgoMemReason"
78
  PUBLICATION_URL = "https://arxiv.org/abs/<arxiv_id>" # placeholder β€” fill in after posting
79
 
80
 
 
74
  34.0, 42.0, 31.0, 27.0, 38.0, 34.0, 34.0),
75
  ]
76
 
77
+ PROJECT_URL = "https://github.com/Ziyang412/EgoMemReason"
78
  PUBLICATION_URL = "https://arxiv.org/abs/<arxiv_id>" # placeholder β€” fill in after posting
79
 
80