We lifted 9 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| srijandas07/clip_baseline_lta_ego4d | canonical | 3 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| round_width | Ran | srijandas07/clip_baseline_lta_ego4d/ego4d/models/video_model_builder.py code served (permissive licence) · get_code("b07e3607b90c1e7c") |
| topk_errors | Ran | srijandas07/clip_baseline_lta_ego4d/ego4d/evaluation/lta_metrics.py code served (permissive licence) · get_code("10e9b4ea0c092f82") |
| topks_correct | Ran | srijandas07/clip_baseline_lta_ego4d/ego4d/evaluation/lta_metrics.py code served (permissive licence) · get_code("eea7a73a4935fff4") |
| distributed_topk_errors | Not yet run | srijandas07/clip_baseline_lta_ego4d/ego4d/evaluation/lta_metrics.py code served (permissive licence) · get_code("b6dd75b900cecbb8") |
| drop_path | Not yet run | srijandas07/clip_baseline_lta_ego4d/ego4d/models/video_model_builder.py code served (permissive licence) · get_code("bcc1cdae3bb3212c") |
| get_loss_func | Not yet run | srijandas07/clip_baseline_lta_ego4d/ego4d/models/losses.py code served (permissive licence) · get_code("dd72775d1ea00db7") |
| get_norm | Not yet run | srijandas07/clip_baseline_lta_ego4d/ego4d/models/batchnorm_helper.py code served (permissive licence) · get_code("952f23f7aff7ce7d") |
| get_trans_func | Not yet run | srijandas07/clip_baseline_lta_ego4d/ego4d/models/resnet_helper.py code served (permissive licence) · get_code("4d6991202a8d6097") |
| is_detection_enabled | Not yet run | srijandas07/clip_baseline_lta_ego4d/ego4d/models/video_model_builder.py code served (permissive licence) · get_code("a99430fceaa1dc2d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action anticipation. Our code is available at github.com/srijandas07/clip_baseline_LTA_Ego4d.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.00579")
get_code_for_paper("2207.00579")
have("2207.00579")
Connect an agent — have() is free.