ST-GD adapts Grounding DINO with about 10 million trainable parameters via adapters and a temporal decoder to achieve competitive performance on limited-data spatio-temporal video grounding benchmarks.
Learning spatiotemporal and motion features in a unified 2d network for action recognition.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 45(3): 3347–3362, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization
ST-GD adapts Grounding DINO with about 10 million trainable parameters via adapters and a temporal decoder to achieve competitive performance on limited-data spatio-temporal video grounding benchmarks.