Papers › XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
Pritam Sarkar, Ali Etemad
We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled videos. XKD is trained with two pseudo objectives. First, masked data reconstruction is performed to learn modality-specific representations from audio and visual streams. Next, self-supervised cross-modal knowledge distillation is performed between the two modalities through a teacher-student setup to learn complementary information. We introduce a novel domain alignment strategy to tackle domain discrepancy between audio and visual modalities enabling effective cross-modal knowledge distillation. Additionally, to develop a general-purpose network capable of handling both audio and visual streams, modality-agnostic variants of XKD are introduced, which use the same pretrained backbone for different audio and visual tasks. Our proposed cross-modal knowledge distillation improves video action classification by 8% to 14% on UCF101, HMDB51, and Kinetics400. Additionally, XKD improves multimodal action classification by 5.5% on Kinetics-Sound. XKD shows state-of-the-art performance in sound classification on ESC50, achieving top-1 accuracy of 96.5%.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
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 |
|---|---|---|---|---|---|---|---|
| Self-Supervised Action Recognition | HMDB51 | XKD (ViT-B/112/16) | Top-1 Accuracy | 69 | #8 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | HMDB51 | XKD-Modality-Agnostic (ViT-B/112/16) | Top-1 Accuracy | 65.9 | #14 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | Kinetics-400 | XKD (ViT-B/112/16) | Top-1 accuracy % | 77.6 | #1 of 4 | Archive leaderboard | report |
| Self-Supervised Action Recognition | Kinetics-400 | XKD (ViT-B/112/16) | Top-5 Accuracy % | 92.9 | #1 of 4 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | XKD (ViT-B/112/16) | 3-fold Accuracy | 94.1 | #9 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | XKD (ViT-B/112/16) | Pre-Training Dataset | Kinetics400 | #9 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | XKD-Modality-Agnostic (ViT-B/112/16) | 3-fold Accuracy | 93.4 | #14 of 53 | 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.
Methods
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