Search Results for author:
Found 13 papers, 10 papers with code
RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework
In this paper, we revisit these issues and propose a novel multi-modal RGB-Event attribute recognition task by drawing inspiration from the advantages of event cameras in low-light, high-speed, and low-power consumption.
VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition
Inspired by the successful application of large models, the introduction of such large models can also be considered to further enhance the performance of multi-modal tasks.
A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation
To this end, we propose a novel stack-propagation framework for learning a generation and understanding pipeline. Specifically, the framework stacks a Transformer encoder and two Transformer decoders, where the first decoder models response generation and the second serves as a regularizer and jointly models response generation and consistency understanding.
SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks
To address this issue, in this paper, we propose a Spiking Neural Network (SNN) based framework for energy-efficient attribute recognition.
MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection
Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges.
Ranked #1 on
Sound Event Detection
on DESED
(PSDS1 metric, using extra
training data)
Language Models are General-Purpose Interfaces
Experimental results across various language-only and vision-language benchmarks show that our model outperforms or is competitive with specialized models on finetuning, zero-shot generalization, and few-shot learning.
Ranked #2 on
Image Captioning
on nocaps val
Visually-Augmented Language Modeling
With the visually-augmented context, VaLM uses a visual knowledge fusion layer to enable multimodal grounded language modeling by attending to both text context and visual knowledge in images.
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task.
BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
Maintaining consistent personas is essential for dialogue agents.
Profile Consistency Identification for Open-domain Dialogue Agents
Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans.
Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines.
Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
Consistency is one of the major challenges faced by dialogue agents.
Exploiting Persona Information for Diverse Generation of Conversational Responses
Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task.
