Search Results for author:
Found 5 papers, 1 papers with code
Action Reimagined: Text-to-Pose Video Editing for Dynamic Human Actions
While existing video editing tasks are limited to changes in attributes, backgrounds, and styles, our method aims to predict open-ended human action changes in video.
UniMODE: Unified Monocular 3D Object Detection
To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors.
Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding
While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length.
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks.
Robustness and Generalization via Generative Adversarial Training
Adversarial training with these examples enable the model to withstand a wide range of attacks by observing a variety of input alterations during training.
