Search Results for author:
Found 28 papers, 16 papers with code
FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions
Specifically, the head pose prediction module is designed to generate head pose sequences from the source face and driving audio.
OPT: One-shot Pose-Controllable Talking Head Generation
To solve the identity mismatch problem and achieve high-quality free pose control, we present One-shot Pose-controllable Talking head generation network (OPT).
Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection
An attempt has been made to get rid of BEV and predict 3D lanes from FV representations directly, while it still underperforms other BEV-based methods given its lack of structured representation for 3D lanes.
Ranked #3 on
3D Lane Detection
on Apollo Synthetic 3D Lane
Bridging Search Region Interaction With Template for RGB-T Tracking
To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module which exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts.
RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval
Sparse sampling is also likely to miss important frames corresponding to some text portions, resulting in textual redundancy.
InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings
Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer.
Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos.
Smoothed Contrastive Learning for Unsupervised Sentence Embedding
Contrastive learning has been gradually applied to learn high-quality unsupervised sentence embedding.
ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding
Unsup-SimCSE takes dropout as a minimal data augmentation method, and passes the same input sentence to a pre-trained Transformer encoder (with dropout turned on) twice to obtain the two corresponding embeddings to build a positive pair.
Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation.
Ranked #7 on
Referring Expression Segmentation
on J-HMDB
LI-Net: Large-Pose Identity-Preserving Face Reenactment Network
Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously.
ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
Our ORDNet is able to extract more comprehensive context information and well adapt to complex spatial variance in scene images.
Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users Based on Weakly Supervised Learning
In this way, we can explicitly exploit the credibility of publishers and users for early fake news detection.
Referring Image Segmentation via Cross-Modal Progressive Comprehension
In addition to the CMPC module, we further leverage a simple yet effective TGFE module to integrate the reasoned multimodal features from different levels with the guidance of textual information.
Ranked #10 on
Referring Expression Segmentation
on RefCOCO testB
Linguistic Structure Guided Context Modeling for Referring Image Segmentation
Referring image segmentation aims to predict the foreground mask of the object referred by a natural language sentence.
Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis
Furthermore, we design a Sentiment-based Rethinking mechanism (SR) by refining the HIN with sentiment label information to learn a more sentiment-aware document representation.
Data Augmentation for Copy-Mechanism in Dialogue State Tracking
While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap between seen slot values (i. e., values that occur in both training set and test set) and unseen ones (values that occur in training set but not in test set).
Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification
Based on the two types of relations, we use a graph convolutional network to learn the deep correlations between styles automatically.
Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots
Existing works mainly focus on matching candidate responses with every context utterance on multiple levels of granularity, which ignore the side effect of using excessive context information.
Ranked #5 on
Conversational Response Selection
on RRS
Jointly embedding the local and global relations of heterogeneous graph for rumor detection
The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal platform for publishing and spreading rumors.
Learning review representations from user and product level information for spam detection
Then, we use orthogonal decomposition and fusion attention to learn a user, review, and product representation from the review information.
TransSent: Towards Generation of Structured Sentences with Discourse Marker
Automatic and human evaluation results show that TransSent can generate structured sentences with high quality, and has certain scalability in different tasks.
"Mask and Infill" : Applying Masked Language Model to Sentiment Transfer
So we propose a two step approach "Mask and Infill".
ESA: Entity Summarization with Attention
Entity summarization aims at creating brief but informative descriptions of entities from knowledge graphs.
Imbalanced Sentiment Classification Enhanced with Discourse Marker
Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data.
AccUDNN: A GPU Memory Efficient Accelerator for Training Ultra-deep Neural Networks
Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming.
Conditional BERT Contextual Augmentation
BERT demonstrates that a deep bidirectional language model is more powerful than either an unidirectional language model or the shallow concatenation of a forward and backward model.
Cross-domain Human Parsing via Adversarial Feature and Label Adaptation
Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences.
