TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction

• URL: http://arxiv.org/abs/2207.00170v1
• Date: Thu, 30 Jun 2022 08:39:52 GMT
• Title: TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction
• Authors: Yuting Wang, Hangning Zhou, Zhigang Zhang, Chen Feng, Huadong Lin, Chaofei Gao, Yizhi Tang, Zhenting Zhao, Shiyu Zhang, Jie Guo, Xuefeng Wang, Ziyao Xu, Chi Zhang
• Abstract summary: We develop a Transformer-based method for input encoding and trajectory prediction. We win the first place of Argoverse 2 Motion Forecasting Challenge with the state-of-the-art brier-minFDE score of 1.90.
• Score: 11.698627151060467
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This technical report presents an effective method for motion prediction in autonomous driving. We develop a Transformer-based method for input encoding and trajectory prediction. Besides, we propose the Temporal Flow Header to enhance the trajectory encoding. In the end, an efficient K-means ensemble method is used. Using our Transformer network and ensemble method, we win the first place of Argoverse 2 Motion Forecasting Challenge with the state-of-the-art brier-minFDE score of 1.90.

Related papers

• Video Motion Transfer with Diffusion Transformers [82.4796313201512]
  We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one. We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal. We apply our strategy to transformer positional embeddings, granting us a boost in zero-shot motion transfer capabilities.
  arXiv  Detail & Related papers  (2024-12-10T18:59:58Z)
• Generalizable Implicit Motion Modeling for Video Frame Interpolation [51.966062283735596]
  Motion is critical in flow-based Video Frame Interpolation (VFI) We introduce General Implicit Motion Modeling (IMM), a novel and effective approach to motion modeling VFI. Our GIMM can be easily integrated with existing flow-based VFI works by supplying accurately modeled motion.
  arXiv  Detail & Related papers  (2024-07-11T17:13:15Z)
• OFMPNet: Deep End-to-End Model for Occupancy and Flow Prediction in Urban Environment [0.0]
  We introduce an end-to-end neural network methodology designed to predict the future behaviors of all dynamic objects in the environment. We propose a novel time-weighted motion flow loss, whose application has shown a substantial decrease in end-point error.
  arXiv  Detail & Related papers  (2024-04-02T19:37:58Z)
• WcDT: World-centric Diffusion Transformer for Traffic Scene Generation [13.616763172038846]
  We introduce a novel approach for autonomous driving trajectory generation by harnessing the complementary strengths of diffusion probabilistic models and transformers. Our proposed framework, termed the "World-Centric Diffusion Transformer"(WcDT), optimize the entire trajectory generation process. Our results show that the proposed approach exhibits superior performance in generating both realistic and diverse trajectories.
  arXiv  Detail & Related papers  (2024-04-02T16:28:41Z)
• Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding [121.08841110022607]
  Existing agent-centric methods have demonstrated outstanding performance on public benchmarks. We introduce the K-nearest neighbor attention with relative pose encoding (KNARPE), a novel attention mechanism allowing the pairwise-relative representation to be used by Transformers. By sharing contexts among agents and reusing the unchanged contexts, our approach is as efficient as scene-centric methods, while performing on par with state-of-the-art agent-centric methods.
  arXiv  Detail & Related papers  (2023-10-19T17:59:01Z)
• Physics-informed Machine Learning for Calibrating Macroscopic Traffic Flow Models [7.422267768764612]
  Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. We propose a novel physics-informed, learning-based calibration approach that achieves performances comparable to and even better than those of optimization-based methods.
  arXiv  Detail & Related papers  (2023-07-12T16:11:57Z)
• Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer [16.457778420360537]
  We propose a novel solution for predicting future trajectories of pedestrians. Our method uses a multimodal encoder-decoder transformer architecture, which takes as input both pedestrian locations and ego-vehicle speeds. We perform detailed experiments and evaluate our method on two popular datasets, PIE and JAAD.
  arXiv  Detail & Related papers  (2023-07-07T18:21:05Z)
• StreamYOLO: Real-time Object Detection for Streaming Perception [84.2559631820007]
  We endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. We consider multiple velocities driving scene and propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively.
  arXiv  Detail & Related papers  (2022-07-21T12:03:02Z)
• Real-time Object Detection for Streaming Perception [84.2559631820007]
  Streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. We build a simple and effective framework for streaming perception. Our method achieves competitive performance on Argoverse-HD dataset and improves the AP by 4.9% compared to the strong baseline.
  arXiv  Detail & Related papers  (2022-03-23T11:33:27Z)
• Attention and Encoder-Decoder based models for transforming articulatory movements at different speaking rates [60.02121449986413]
  We propose an encoder-decoder architecture using LSTMs which generates smoother predicted articulatory trajectories. We analyze amplitude of the transformed articulatory movements at different rates compared to their original counterparts. We observe that AstNet could model both duration and extent of articulatory movements better than the existing transformation techniques.
  arXiv  Detail & Related papers  (2020-06-04T19:33:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.