Avg
44 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Avg
Most implemented papers
What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
ParitoshParmar/MTL-AQA
•
•
CVPR 2019
Can performance on the task of action quality assessment (AQA) be improved by exploiting a description of the action and its quality?
A Comparison of deep learning methods for environmental sound
lijuncheng16/AudioTaggingDoneRight
•
•
On these features, we apply five models: Gaussian Mixture Model (GMM), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Convolutional Deep Neural Net- work (CNN) and i-vector.
Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging.
Testing DNN Image Classifiers for Confusion & Bias Errors
We found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others.
BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition
awslabs/speech-representations
•
•
We introduce BERTphone, a Transformer encoder trained on large speech corpora that outputs phonetically-aware contextual representation vectors that can be used for both speaker and language recognition.
Mitigating large adversarial perturbations on X-MAS (X minus Moving Averaged Samples)
stonylinux/mitigating_large_adversarial_perturbations_on_X-MAS
•
•
We propose the scheme that mitigates the adversarial perturbation $\epsilon$ on the adversarial example $X_{adv}$ ($=$ $X$ $\pm$ $\epsilon$, $X$ is a benign sample) by subtracting the estimated perturbation $\hat{\epsilon}$ from $X$ $+$ $\epsilon$ and adding $\hat{\epsilon}$ to $X$ $-$ $\epsilon$.
DEXA: Supporting Non-Expert Annotators with Dynamic Examples from Experts
of 0. 68 to experts in DEXA vs. 0. 40 in CONTROL); (ii) already three per majority voting aggregated annotations of the DEXA approach reach substantial agreements to experts of 0. 78/0. 75/0. 69 for P/I/O (in CONTROL 0. 73/0. 58/0. 46).
A Symbolic Temporal Pooling method for Video-based Person Re-Identification
aru05c/SymbolicTemporalPooling
•
•
In video-based person re-identification, both the spatial and temporal features are known to provide orthogonal cues to effective representations.
Revealing the Myth of Higher-Order Inference in Coreference Resolution
lxucs/coref-hoi
•
•
EMNLP 2020
We find that given a high-performing encoder such as SpanBERT, the impact of HOI is negative to marginal, providing a new perspective of HOI to this task.
CNN Model & Tuning for Global Road Damage Detection
We briefly describe the tuning strategy for the experiments conducted on two-stage Faster R-CNN with Deep Residual Network (Resnet) and Feature Pyramid Network (FPN) backbone.
