32 accepted papers
Predicting street-level socioeconomic indicators from street view imagery is fundamental to urban planning. Existing methods typically extract visual features via pretrained encoders and propagate information through graph-based learning, but they fail to fully exploit the structured, task-relevant,…
Singing Voice Conversion (SVC) aims to transform a source singing voice into a target singer while preserving lyrics and melody. Most existing SVC methods depend on F0 extractors to capture the lead melody from clean vocals. However, no existing method can reliably extract clean vocals from accompan…
Hateful meme classification aims to identify memes containing hateful content and has become increasingly important in the era of social media dominance. Large multimodal models (LMMs) have significantly enhanced the understanding of multimodal content, advancing this field. However, cognitive biase
Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeable performance degradation, while Mixture-of-Experts (MoE) models require extensive computational resources. In this paper, we propose L0-MoE, a ligh…
In this paper, we introduce AutoMV, an autonomous agent framework designed for generating real estate marketing videos. The framework integrates a diverse set of existing models into a tool library, allowing the agent to intelligently select and execute the appropriate tools. Given property images a…
Learning urban region embeddings has substantially advanced urban analysis, but their typical focus on individual cities leads to disparate embedding spaces, hindering cross-city knowledge transfer and the reuse of downstream task predictors. To tackle this issue, we present Consistent Region Embedd…
As large language models (LLMs) continue to evolve, leaderboards play a significant role in steering their development. Existing leaderboards often prioritize model capabilities while overlooking safety concerns, leaving a significant gap in responsible AI development. To address this gap, we introd…
Large language models (LLMs) have shown impressive performance in code understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data synthesis and filtering techniques have been widely adopted and sho…
The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect its the growing complexity and diversity of workloads. Unlike prior challenge…
Transformer-based Large Language Models (LLMs) have become increasingly important. However, scaling LLMs to longer contexts incurs slow inference speed and high GPU memory consumption for caching key-value (KV) vectors. This paper presents RetrievalAttention, a training-free approach to both acceler…
Origin-Destination (OD) demand prediction is a pivotal yet highly challenging task in intelligent transportation systems, aiming to accurately forecast cross-region ridership flows within urban networks. While previous studies have focused on modeling node-to-node relationships, most of them neglect
The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is crucial, especially given the threat of 3D physical attacks that
Semantic annotation for points of interest (POIs) is the process of annotating a POI with a category label, which facilitates many services related to POIs, such as POI search and recommendation. Most of the existing solutions extract features related to POIs from abundant user-generated content dat…
Multimodal sarcasm detection, aiming to detect the ironic sentiment within multimodal social data, has gained substantial popularity in both the natural language processing and computer vision communities. Recently, graph-based studies by drawing sentimental relations to detect multimodal sarcasm ha…
Points of interest (POIs) carry a wealth of semantic information of varying locations in cities and thus have been widely used to enable various location-based services. To understand POI semantics, existing methods usually model contextual correlations of POI categories in users' check-in sequences…
Recently, learning urban region representations utilizing multi-modal data (information views) has become increasingly popular, for deep understanding of the distributions of various socioeconomic features in cities. However, previous methods usually blend multi-view information in a posteriors stag…
Dialogue representation and understanding aim to convert conversational inputs into embeddings and fulfill discriminative tasks. Compared with free-form text, dialogue has two important characteristics, hierarchical semantic structure and multi-facet attributes. Therefore, directly applying the pret…
Empathy is a crucial factor in open-domain conversations, which naturally shows one’s caring and understanding to others. Though several methods have been proposed to generate empathetic responses, existing works often lead to monotonous empathy that refers to generic and safe expressions. In this p…
Dense video captioning aims to localize multiple events from an untrimmed video and generate corresponding captions for each event. Fusing different modalities(e.g. rgb, flow, audio) via transformer structure is a promising way to improve the caption performance. However, it is challenging for the c…
Disfluency detection aims to recognize disfluencies in sentences. Existing works usually adopt a sequence labeling model to tackle this task. They also attempt to integrate into models the feature that the disfluencies are similar to the correct phrase, the so-called "rough copy". However, they heav…
Multimodal named entity recognition (MNER) is a critical step in information extraction, which aims to detect entity spans and classify them to corresponding entity types given a sentence-image pair. Existing methods either (1) obtain named entities with coarse-grained visual clues from attention me…
With the popularity of social media, detecting sentiment from multimodal posts (e.g. image-text pairs) has attracted substantial attention recently. Existing works mainly focus on fusing different features but ignore the challenge of modality heterogeneity. Specifically, different modalities with in…
Categories of Point of Interest (POI) facilitate location-based services from many aspects like location search and POI recommendation. However, POI categories are often incomplete and new POIs are being consistently generated, this rises the demand for semantic annotation for POIs, i.e., labeling t…
In this paper, we propose a Unified pre-training Framework for Online and Offline (UFO2) Automatic Speech Recognition (ASR), which 1) simplifies the two separate training workflows for online and offline modes into one process, and 2) improves the Word Error Rate (WER) performance with limited utter…
Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the pho…
Few-shot table understanding is a critical and challenging problem in real-world scenario as annotations over large amount of tables are usually costly. Pre-trained language models (PLMs), which have recently flourished on tabular data, have demonstrated their effectiveness for table understanding t…
Turn-taking, aiming to decide when the next speaker can start talking, is an essential component in building human-robot spoken dialogue systems. Previous studies indicate that multi-modal cues can facilitate this challenging task. However, due to the paucity of public multimodal datasets, current m…
Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not fully explored, especially for the natural language understanding classificatio…
In this paper, we present a novel system (denoted as Polaca) to generate poetic Chinese landscape painting with calligraphy. Unlike previous single image-to-image painting generation, Polaca takes the classic poetry as input and outputs the artistic landscape painting image with the corresponding ca…
Context modeling plays a critical role in building multi-turn dialogue systems. Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting the conversational query into a self-contained utterance. However, existing approa…
Auto-exploration is a task for self-driving robots to explore unknown environments, which becomes much complicated when they move on irregular outdoor terrains. To improve the situation, a new frontier-based exploration algorithm is presented in this paper. It starts from original 3D cloud points of…
Depending on a humanoid finger sensor with multimodal perception capability, physical properties such as pressure, temperature, texture features, surface roughness, micro vibration, etc., could be easily extracted when the sensor contacts with different objects. In this paper, an innovative calibrat…