Polar Relative Positional Encoding for Video-Language Segmentation

Authors: Ke Ning, Lingxi Xie, Fei Wu, Qi Tian

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our method outperforms previous best method by a large margin of 11.4% absolute improvement in terms of m AP on the challenging A2D Sentences dataset. Our method also achieves competitive performances on the J-HMDB Sentences dataset. We evaluate our approach on two challenging datasets: A2D Sentences and J-HMDB Sentences.
Researcher Affiliation Collaboration Ke Ning1 , Lingxi Xie2 , Fei Wu1 and Qi Tian2 1Zhejiang University 2Huawei Noah s Ark Lab
Pseudocode No The paper describes its methods but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets Yes A2D Sentences dataset is an extended version of the A2D dataset [Xu et al., 2015]. J-HMDB Sentences is an extension of the J-HMDB dataset [Jhuang et al., 2013].
Dataset Splits No The paper specifies training and testing video counts (e.g., '3,036 training videos and 746 testing videos' for A2D Sentences) but does not explicitly provide details for a separate validation split.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper states 'We use Tensor Flow to implement our model.' but does not provide specific version numbers for TensorFlow or any other software dependencies.
Experiment Setup Yes Implementation Details. We use Tensor Flow to implement our model. p is set to 3 in our experiments. The learning rate is 0.0005. We use a stack of 8 256 256 RGB frames as the video input for a balanced performance and speed.