Papers › SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition
Xijun Wang, Ruiqi Xian, Tianrui Guan, Fuxiao Liu, Dinesh Manocha
We present a new learning approach, Soft Conditional Prompt Learning (SCP), which leverages the strengths of prompt learning for aerial video action recognition. Our approach is designed to predict the action of each agent by helping the models focus on the descriptions or instructions associated with actions in the input videos for aerial/robot visual perception. Our formulation supports various prompts, including learnable prompts, auxiliary visual information, and large vision models to improve the recognition performance. We present a soft conditional prompt method that learns to dynamically generate prompts from a pool of prompt experts under different video inputs. By sharing the same objective with the task, our proposed SCP can optimize prompts that guide the model's predictions while explicitly learning input-invariant (prompt experts pool) and input-specific (data-dependent) prompt knowledge. In practice, we observe a 3.17-10.2% accuracy improvement on the aerial video datasets (Okutama, NECDrone), which consist of scenes with single-agent and multi-agent actions. We further evaluate our approach on ground camera videos to verify the effectiveness and generalization and achieve a 1.0-3.6% improvement on dataset SSV2. We integrate our method into the ROS2 as well.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Recognition | Okutama-Action | PLAR with bbox (Ours) | Accuracy | 75.93 | #1 of 2 | Archive leaderboard | report |
| Action Recognition | Okutama-Action | PLAR without bbox (Ours) | Accuracy | 71.54 | #2 of 2 | Archive leaderboard | report |
| Action Recognition | Something-Something V2 | PLAR | Top-1 Accuracy | 67.3 | #66 of 123 | Archive leaderboard | report |
| Action Recognition | Something-Something V2 | PLAR | Top-5 Accuracy | 91 | #66 of 123 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections