85 accepted papers
Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4D perception and temporal understanding. Existing 3D and 4D Video Question Answering (VQA) benchmarks also emphasize static scenes and lack region-level
Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy
Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; however, current parameter-efficient fine-tuning (PEFT) methods remain largely limited to single-task adaptation. We introduce Free Sinewich, a parameter-efficient multi-task learning framework that enables
Large-scale vision-language models (VLMs) have recently achieved remarkable multimodal understanding, but their massive size makes them impractical for deployment on mobile or edge devices. This raises the need for compact yet capable VLMs that can efficiently learn from powerful large teacher. Howe
Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. We introduce OmniVinci, an initiative to build a strong, open-source, omni-modal LLM. We carefully study the design choices across model architecture and data curati…
We propose OpenVoxel, a training-free algorithm for grouping and captioning sparse voxels for the open-vocabulary 3D scene understanding tasks. Given the sparse voxel rasterization (SVR) model obtained from multi-view images of a 3D scene, our OpenVoxel is able to produce meaningful groups that desc
Video Large Language Models (VideoLLMs) have shown remarkable progress in video understanding. However, these models still struggle to effectively perceive and exploit rich temporal information in videos when responding to user queries. Therefore, they often generate descriptions of events that are
Aligning Large Language Models (LLMs) with human preferences through finetuning is resource-intensive, motivating lightweight alternatives at test time. We address test-time alignment through the lens of sequential decision making, a perspective that reveals two fundamental challenges. When actions…
Current state-of-the-art autonomous vehicles could face safety critical situations when their local sensors are occluded by large objects on the road nearby. Vehicle-to-vehicle (V2V) cooperative autonomous driving is proposed to address this problem. More recent work further adopts a new approach th…
Current autonomous driving vehicles rely mainly on their individual sensors to understand surrounding scenes and plan for future trajectories, which can be unreliable when the sensors are malfunctioning or occluded. To address this problem, cooperative perception methods via vehicle-to-vehicle (V2V)…
When performing 3D inpainting using novel-view rendering methods like Neural Radiance Field (NeRF) or 3D Gussian Splatting (3DGS), how to achieve texture and geometry consistency across camera views has been a challenge. In this paper, we propose a framework of 3D Gaussian Inpainting with Depth-Guid…
Gender bias in vision-language foundation models (VLMs) raises concerns about their safe deployment and is typically evaluated using benchmarks with gender annotations on real-world images. However, as these benchmarks often contain spurious correlations between gender and non-gender features, such…
Updating diffusion models in an incremental setting would be practical in real-world applications yet computationally challenging. We present a novel learning strategy of Concept Neuron Selection, a simple yet effective approach to perform personalization in a continual learning scheme. CNS uniquely…
Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs) by incorporating pre-trained speech models. However, these SLMs often undergo extensive speech instruction-tuning to bridge the gap between speech and text modalities. This requires si…
We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on a rendering process, our method directly associates language-aligned CLIP embeddings with 3D Gaussians for holistic 3D s…
Open-source foundation models have seen rapid adoption and development, enabling powerful general-purpose capabilities across diverse domains. However, fine-tuning large foundation models for domain-specific or personalized tasks remains prohibitively expensive for most users due to the significant…
We tackle open-vocabulary 3D scene segmentation tasks by introducing a novel data generation pipeline and training framework. Our work targets three essential aspects required for an effective dataset: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale.…
We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the vis…
Large-scale vision-language models, such as CLIP, are known to contain societal bias regarding protected attributes (e.g., gender, age). This paper aims to address the problems of societal bias in CLIP. Although previous studies have proposed to debias societal bias through adversarial learning or t…
Amodal instance segmentation, which aims to detect and segment both visible and invisible parts of objects in images, plays a crucial role in various applications, including autonomous driving, robotic manipulation, and scene understanding. While existing methods require training both front-end dete…
It is challenging to update Large language models (LLMs) since real-world knowledge evolves. While existing Lifelong Knowledge Editing (LKE) methods efficiently update sequentially incoming edits, they often struggle to precisely overwrite the outdated knowledge with the latest one, resulting in con…
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The first is to adaptively and explicitly allocate sparse voxels t…
Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end fashion, directly mapping inputs to actions without explicit re…
Audio-Visual Video Parsing (AVVP) entails the challenging task of localizing both uni-modal events (i.e., those occurring exclusively in either the visual or acoustic modality of a video) and multi-modal events (i.e., those occurring in both modalities concurrently). Moreover, the prohibitive cost o…
Pre-training and representation learning have been playing an increasingly important role in modern speech processing. Nevertheless, different applications have been relying on different foundation models, since predominant pre-training techniques are either designed for discriminative tasks or gen…
Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful,…
The recent surge in high-quality visual instruction tuning samples from closed-source vision-language models (VLMs) such as GPT-4V has accelerated the release of open-source VLMs across various model sizes. However, scaling VLMs to improve performance using larger models brings significant computati…
Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multipl…
Imitation learning aims to learn a policy from observing expert demonstrations without access to reward signals from environments. Generative adversarial imitation learning (GAIL) formulates imitation learning as adversarial learning, employing a generator policy learning to imitate expert behaviors…
Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first in…
The selection of violin fingerings is influenced by factors such as musical context, skill level, and personal taste. Current deep-learningbased models, relying solely on symbolic data, are able to generate playable fingerings but struggle to capture the personal nuances of musical performance, whic…
Utilizing multi-view inputs to synthesize novel-view images Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work we introduce a Generalizable Semantic Neural Radiance Field (GSNeRF) which uniquely takes image semantics into the synthesis process so that b…
Federated Learning (FL) is an emerging paradigm that enables multiple users to collaboratively train a robust model in a privacy-preserving manner without sharing their private data. Most existing approaches of FL only consider traditional single-label image classification, ignoring the impact when…
Natural Language Explanation (NLE) in vision and language tasks aims to provide human-understandable explanations for the associated decision-making process. In practice, one might encounter explanations which lack informativeness or contradict visual-grounded facts, known as implausibility and hall…
We introduce ReXTime, a benchmark designed to rigorously test AI models' ability to perform temporal reasoning within video events. Specifically, ReXTime focuses on reasoning across time, i.e. human-like understanding when the question and its corresponding answer occur in different video segments.…
"Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable. The former refrains the model from producing images associ…
"We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model ar…
State-of-the-art single-view 360 room layout reconstruction methods formulate the problem as a high-level 1D (per-column) regression task. On the other hand traditional low-level 2D layout segmentation is simpler to learn and can represent occluded regions but it requires complex post-processing for…
"Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting of previously learned knowledge and a reduction in zero-shot classification per…
Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label collection. To solve this problem, we propose VQScore, a self-su…
"Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization time for both training and inference, the use of GAN-based m…
Learning models trained on biased datasets tend to observe correlations between categorical and undesirable features, which result in degraded performances. Most existing debiased learning models are designed for centralized machine learning, which cannot be directly applied to distributed settings…
Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy. Recently, large-scale pre-trained models (e.g., Vision Transformer) have shown a strong capability of deriving robust representa…
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid…
End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent’s insensitivity to subtle c…
Audio-visual learning has been a major pillar of multi-modal machine learning, where the community mostly focused on its $\textit{modality-aligned}$ setting, $\textit{i.e.}$, the audio and visual modality are $\textit{both}$ assumed to signal the prediction target. With the Look, Listen, and Parse d…
Low-light image enhancement aims to improve the visual quality of images captured under poor lighting conditions. While recent works have successfully developed deep learning-based solutions, a large number of existing works require ground-truth normal-light images during training, and most methods…
We tackle the problem of target-free text-guided image manipulation, which requires one to modify the input reference image based on the given text instruction, while no ground truth target image is observed during training. To address this challenging task, we propose a Cyclic-Manipulation GAN (cMa…
As a key characteristic in audio-visual speech recognition (AVSR), relating linguistic information observed across visual and audio data has been a challenge, benefiting not only audio/visual speech recognition (ASR/VSR) but also for manipulating data within/across modalities. In this paper, we pres…
Few-shot classification requires one to classify instances of novel classes, given only a few examples of each class. Although promising meta-learning methods have been proposed recently, there is no guarantee that existing solutions would generalize to novel classes from an unseen domain. In this p…
We present Neural Mixtures of Planar Experts (NeurMiPs), a novel planar-based scene representation for modeling geometry and appearance. NeurMiPs leverages a collection of local planar experts in 3D space as the scene representation. Each planar expert consists of the parameters of the local rectang…
Novel object captioning (NOC) aims to describe images containing objects without observing their ground truth captions during training. Due to the absence of caption annotation, captioning models cannot be directly optimized via sequence-to-sequence training or CIDEr optimization. As a result, we pr…
Point cloud completion is an active research topic for 3D vision and has been widely studied in recent years. Instead of directly predicting missing point cloud from the partial input, we introduce a Semantic-Prototype Variational Transformer (SPoVT) in this work, which takes both partial point clou…
In this paper, we address the task of semantics-guided image outpainting, which is to complete an image by generating semantically practical content. Different from most existing image outpainting works, we approach the above task by understanding and completing image semantics at the scene graph le…
Domain generalization (DG) aims to transfer the learning task from a single or multiple source domains to unseen target domains. To extract and leverage the information which exhibits sufficient generalization ability, we propose a simple yet effective approach of Adversarial Teacher-Student Represe…
Human perceives rich auditory experience with distinct sound heard by ears. Videos recorded with binaural audio particular simulate how human receives ambient sound. However, a large number of videos are with monaural audio only, which would degrade the user experience due to the lack of ambient inf…
When translating text inputs into layouts or images, existing works typically require explicit descriptions of each object in a scene, including their spatial information or the associated relationships. To better exploit the text input, so that implicit objects or relationships can be properly infe…
Point clouds are among the popular geometry representations for 3D vision applications. However, without regular structures like 2D images, processing and summarizing information over these unordered data points are very challenging. Although a number of previous works attempt to analyze point cloud…
Searching actors from videos by a single portrait image is a challenging task, due to large variations of video scenes and intra-person appearance. To tackle this problem, most recent works apply deep neural networks for detecting and extracting robust facial features for matching. However, when the…
Human face reenactment aims at transferring motion patterns from one face (from a source-domain video) to an-other (in the target domain with the identity of interest).While recent works report impressive results, they are notable to handle multiple identities in a unified model. In this paper, we p…
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like in person re-identification or image retrieval. Our learnin…
To rectify fisheye distortion from a single image, we advance self-supervised learning strategies and propose a unique deep learning model of Fisheye GAN (FE-GAN). Our FE-GAN learns pixel-level distortion flow from sets of fisheye distorted images and distortion-free ones (but not requiring such cor…
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison d…
Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. To address this challenging task, existing re-ID models typically rely on a large amount of labeled training data, which is not practical for real-world applications. To alleviate this li…
Audio-visual event localization requires one to identify the event which is both visible and audible in a video (either at a frame or video level). To address this task, we propose a deep neural network named Audio-Visual sequence-to-sequence dual network (AVSDN). By jointly taking both audio and vi…
3D reconstruction, inferring 3D shape information from a single 2D image, has drawn attention from learning and vision communities. In this paper, we propose a framework for learning pose-aware 3D shape reconstruction. Our proposed model learns deep representation for recovering the 3D object, with…
Generative Adversarial Network (GAN) has been widely applied on Single Image Super-Resolution (SISR) problems. However, there can be quite a variability in the results from the GAN-based methods. In some cases, the GAN-based methods might cause structure distortion, which can be easily distinguished…
Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade person re-ID performance in real-world scenarios. To overcome this problem, we…
Few-shot learning (FSL) requires one to learn from object categories with a small amount of training data (as novel classes), while the remaining categories (as base classes) contain a sufficient amount of data for training. It is often desirable to transfer knowledge from the base classes and deriv…
Monocular depth estimation is a challenging task in scene understanding, with the goal to acquire the geometric properties of 3D space from 2D images. Due to the lack of RGB-depth image pairs, unsupervised learning methods aim at deriving depth information with alternative supervision such as stereo…
We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. Realized by adversarial training with additional ability to exploit domain-specific information, the proposed network is able to perform continuous c…
In order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data. Since such annotation process is in general costly, we focus on the learning task of weakly-supervised multi-label classification (WS-MLC). In…
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However, one cannot easily address this task without observing ground…
In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge between objects of interests, we propose a framework that inc…
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage. However, most existing studies rely on training data of third-person videos, which cannot easily generalize to highlight the first-person one…
Real-world visual classification tasks typically need to deal with data observed from different domains. Inspired by canonical correlation analysis (CCA), we propose an enhanced CCA with local density for associating and recognizing cross-domain data. In addition to maximizing the correlation of the…
In this paper, we advocate the use of Grassmann manifolds for discovering object images in different states (e.g., unripe, peeled, etc.). We propose a novel dictionary learning algorithm, which derives the subspaces on a Grassmann manifold for describing each object state. By our introduced geodesic…
Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases. Instead of collecting a large number of annotated image…
In this paper, we address the problem of detecting and segmenting partial image blur from a single input image. Instead of assuming particular image priors or requiring additional user annotation, we propose a novel learning framework which jointly solves the tasks of blur kernel estimation and imag…
Domain adaptation is a challenging task, since it associates data collected from different domains or exhibiting distinct distributions. In this paper, we particularly focus on adapting cross-domain data with distinct feature dimensions or representations. Thus, this is referred to as the task of he…
While domain adaptation (DA) aims to associate the learning tasks across data domains, heterogeneous domain adaptation (HDA) particularly deals with learning from cross-domain data which are of different types of features. In other words, for HDA, data from source and target domains are observed in…
It has been a challenging task to identify and distinguish between images of different styles. The challenges mainly come from the extraction of high-level image semantic information, and the presence of the associated ambiguity. In this work, we propose a ranking model for style identification. Giv…
Visual summarization addresses the task of selecting images from an image collection, so that the sampled images would contain representative information which sufficiently highlights the collected visual data. In this paper, we solve the problem of style-centric visual summarization using photograp…
In this paper, we propose the propagation filter as a novel image filtering operator, with the goal of smoothing over neighboring image pixels while preserving image context like edges or textural regions. In particular, our filter does not to utilize explicit spatial kernel functions as bilateral a…
We address a challenging unsupervised domain adaptation problem with imbalanced cross-domain data. For standard unsupervised domain adaptation, one typically obtains labeled data in the source domain and only observes unlabeled data in the target domain. However, most existing works do not consider…