Search Results for author:
Found 50 papers, 22 papers with code
Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation
Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements.
ASM: Adaptive Sample Mining for In-The-Wild Facial Expression Recognition
First, the Adaptive Threshold Learning module generates two thresholds, namely the clean and noisy thresholds, for each category.
Facial Expression Recognition
Facial Expression Recognition (FER)
DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
However, it is difficult to restore the lost details in the dark area by relying only on the RGB domain.
PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine
Moreover, to enhance stability of the prompt effect evaluation, we propose a novel prompt bagging method involving forward and backward thinking, which is superior to majority voting and is beneficial for both feedback and weight calculation in boosting.
Revisiting Neural Retrieval on Accelerators
A key component of retrieval is to model (user, item) similarity, which is commonly represented as the dot product of two learned embeddings.
Bi-ViT: Pushing the Limit of Vision Transformer Quantization
Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices.
Long-Term Rhythmic Video Soundtracker
To this end, we present Long-Term Rhythmic Video Soundtracker (LORIS), a novel framework to synthesize long-term conditional waveforms.
Enhancing Personalized Ranking With Differentiable Group AUC Optimization
AUC is a common metric for evaluating the performance of a classifier.
Spatial-temporal Transformer for Affective Behavior Analysis
The in-the-wild affective behavior analysis has been an important study.
Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos
The continuous improvement of human-computer interaction technology makes it possible to compute emotions.
Facial Affect Recognition based on Transformer Encoder and Audiovisual Fusion for the ABAW5 Challenge
In this paper, we present our solutions for the 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW), which includes four sub-challenges of Valence-Arousal (VA) Estimation, Expression (Expr) Classification, Action Unit (AU) Detection and Emotional Reaction Intensity (ERI) Estimation.
Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields
Common capture low-light scenes are challenging for most computer vision techniques, including Neural Radiance Fields (NeRF).
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part.
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
Hybrid Multimodal Fusion for Humor Detection
Our experiments demonstrate the effectiveness of our proposed model and hybrid fusion strategy on multimodal fusion, and the AUC of our proposed model on the test set is 0. 8972.
Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis
In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges.
Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
Existing solutions to this problem estimate a single image sequence without considering the motion ambiguity for each region.
Extreme Masking for Learning Instance and Distributed Visual Representations
The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously.
Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations
We propose an unsupervised method for 3D geometry-aware representation learning of articulated objects, in which no image-pose pairs or foreground masks are used for training.
Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
In this paper, instead of two consecutive frames, we propose to exploit a pair of images captured by dual RS cameras with reversed RS directions for this highly challenging task.
A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
Concretely, we pretrain the sign-to-gloss visual network on the general domain of human actions and the within-domain of a sign-to-gloss dataset, and pretrain the gloss-to-text translation network on the general domain of a multilingual corpus and the within-domain of a gloss-to-text corpus.
Ranked #2 on
Sign Language Translation
on CSL-Daily
Robust facial expression recognition with global‑local joint representation learning
In the proposed method, (1) the topological structure information and texture feature of regions of interest (ROIs) are modeled as graphs and processed with graph convolutional network (GCN) to remain the topological features.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition
Typically in recent work, the pseudo-labels are obtained by training a model on the labeled data, and then using confident predictions from the model to teach itself.
Towards Tokenized Human Dynamics Representation
For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking.
Self-supervised Discovery of Human Actons from Long Kinematic Videos
However, methods for understanding short semantic actions cannot be directly translated to long kinematic sequences such as dancing, where it becomes challenging even to semantically label the human movements.
ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection
A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution.
Ranked #40 on
Human-Object Interaction Detection
on HICO-DET
4-bit Quantization of LSTM-based Speech Recognition Models
We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition (ASR): hybrid Deep Bidirectional LSTM - Hidden Markov Models (DBLSTM-HMMs) and Recurrent Neural Network - Transducers (RNN-Ts).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory.
Ranked #20 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
This paper presents a computational framework that generates ensemble predictive mechanics models with uncertainty quantification (UQ).
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Large-scale distributed training of Deep Neural Networks (DNNs) on state-of-the-art platforms is expected to be severely communication constrained.
Neural Articulated Radiance Field
We present Neural Articulated Radiance Field (NARF), a novel deformable 3D representation for articulated objects learned from images.
Ultra-Low Precision 4-bit Training of Deep Neural Networks
In this paper, we propose a number of novel techniques and numerical representation formats that enable, for the very first time, the precision of training systems to be aggressively scaled from 8-bits to 4-bits.
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach
With the reduced dimensionality of less relevant body areas, the training set distribution within network branches more closely reflects the statistics of local poses instead of global body poses, without sacrificing information important for joint inference.
Ranked #19 on
Monocular 3D Human Pose Estimation
on Human3.6M
Detecting Human-Object Interactions with Action Co-occurrence Priors
A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution.
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person.
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
Reducing the numerical precision of data and computation is extremely effective in accelerating deep learning training workloads.
SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation
Point cloud analysis has drawn broader attentions due to its increasing demands in various fields.
Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets
A multiscale shared convolution structure is adopted in the discriminator network to further supervise training the generator.
Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers.
Explicit Spatiotemporal Joint Relation Learning for Tracking Human Pose
We present a method for human pose tracking that is based on learning spatiotemporal relationships among joints.
An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge
For the ECCV 2018 PoseTrack Challenge, we present a 3D human pose estimation system based mainly on the integral human pose regression method.
Ranked #1 on
3D Human Pose Estimation
on CHALL H80K
A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation
Traditional neural language models tend to generate generic replies with poor logic and no emotion.
Integral Human Pose Regression
State-of-the-art human pose estimation methods are based on heat map representation.
Ranked #23 on
Pose Estimation
on MPII Human Pose
Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.
2D Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+4
Compositional Human Pose Regression
A central problem is that the structural information in the pose is not well exploited in the previous regression methods.
Ranked #36 on
Pose Estimation
on MPII Human Pose
Deep Kinematic Pose Regression
In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation.
Ranked #302 on
3D Human Pose Estimation
on Human3.6M
Cascaded Hand Pose Regression
We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects.
Realtime and Robust Hand Tracking from Depth
We present a realtime hand tracking system using a depth sensor.
