47 accepted papers
Recent advancements in multimodal large language models for video understanding (videoLLMs) have enhanced their capacity to process complex spatiotemporal data. However, challenges such as factual inaccuracies, harmful content, biases, hallucinations, and privacy risks compromise their reliability.
Knowledge Graph Question Answering (KGQA) aims to improve factual accuracy by leveraging structured knowledge. However, real-world Knowledge Graphs (KGs) are often incomplete, leading to the problem of Incomplete KGQA (IKGQA). A common solution is to incorporate external data to fill knowledge gaps,
Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities in both large language models (LLMs) and multimodal large language models (MLLMs). However, its reliability is often undermined by the accumulation of errors in intermediate steps. This paper proposes a novel ap
Drag-Based Image Editing (DBIE), which allows users to manipulate images by directly dragging objects within them, has recently attracted much attention from the community. However, it faces two key challenges: (i) point-based drag is often highly ambiguous and difficult to align with user intention
Large Language Models (LLMs) excel in various domains, but their safe deployment faces the challenge of balancing safety and utility. Existing alignment strategies often strengthen refusal mechanisms to reduce harmful outputs, but harmless instructions with superficial risky words are mistakenly rej…
Large Language Models (LLMs) have achieved remarkable success in recent years, owing to their impressive generalization capabilities and rich world knowledge. To capitalize on the potential of using LLMs as recommender systems, mainstream approaches typically focus on two paradigms. The first paradi
Safety alignment remains brittle under domain shift and noisy preference supervision. Existing robust alignment methods predominantly focus on data uncertainty in alignment data, while being less effective at addressing failures caused by optimization-induced fragility. In this work, we revisit robu…
Time series forecasting (TSF) plays a crucial role in many real-world applications, such as weather prediction and economic planning. While Transformer-based models have shown strong capabilities in modeling long-range dependencies, effectively capturing the multi-scale temporal dynamics inherent in
Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose \textbf{stReaming drag-oriEnted interactiVe vidEo manipuLation (R…
Joint Energy-based Models (JEMs) are well known for their ability to unify classification and generation within a single framework. Despite their promising generative and discriminative performance, their robustness remains far inferior to adversarial training (AT), which, conversely, achieves stron
Existing continual learning works explored strategies like memory replay, regularization, and parameter isolation, but little analysis was conducted on the optimization behavior of LLMs’ continual fine-tuning. In this work, we investigate the geometric connections of different minima along the conti…
Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed in resource-constrained mobile devices, due to suffering from either few efficiency gains or significant accuracy drops.…
Generating continuous sign language videos from discrete segments is challenging due to the need for smooth transitions that preserve natural flow and meaning. Traditional approaches that simply concatenate isolated signs often result in abrupt transitions, disrupting video coherence. To address thi…
We present EgoBlind, the first egocentric VideoQA dataset collected from blind individuals to evaluate the assistive capabilities of contemporary multimodal large language models (MLLMs). EgoBlind comprises 1,392 first-person videos from the daily lives of blind and visually impaired individuals. It…
Low-light image enhancement (LLIE) aims to improve the visual quality of images captured under poor lighting conditions. In supervised LLIE tasks, there exists a significant yet often overlooked inconsistency between the overall brightness of an enhanced image and its ground truth counterpart, refer…
This paper tackles the challenge of stereoscopic image rain removal by focusing on enhancing texture integrity and disparity consistency. Existing stereoscopic rain removal techniques often fall short due to 1) disruptions in texture coherence caused by complex rain streaks, and 2) inaccuracies in d…
A major challenge in Low-Light Image Enhancement (LLIE) is its ill-posed nature: low-light images often lack sufficient information to align with normal-light ones (e.g., not all training data can be fully fitted to the ground truth). Numerous studies have attempted to bridge the gap between low- an…
Sign Language Production (SLP) aims to generate sign videos corresponding to spoken language sentences, where the conversion of sign Glosses to Poses (G2P) is the key step. Due to the cross-modal semantic gap and the lack of word-action correspondence labels for strong supervision alignment, the SLP…
Score-based Generative Models (SGMs) have demonstrated remarkable generalization capabilities, e.g. generating unseen, but natural data. However, the greater the generalization power, the more likely the unintended generalization, and the more dangerous the abuse. Despite these concerns, research on…
Intent-based grasp generation inherently involves challenges such as manipulation ambiguity and modality gaps. To address these, we propose a novel Retrieval-Augmented Grasp Generation model (RAGG). Our key insight is that when humans manipulate new objects, they initially mimic the interaction patt…
Recent progress in text–video retrieval has been largely driven by contrastive learning. However, existing methods often overlook the effect of the modality gap, which causes anchor representations to undergo in-place optimization (i.e., optimization tension) that limits their alignment capacity. Mo…
Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in video frames based on the associated audio signal. Prevailing AVS methods typically adopt an audio-centric Transformer architecture, where object queries are derived from audio features. However, audio-centric Transformers su…
Multimodal large language models (MLLMs) demonstrate impressive capabilities by integrating visual and textual information. However, the incorporation of visual modalities also introduces new and complex safety risks, rendering even the most advanced models vulnerable to sophisticated jailbreak atta
Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as discrete three-dimensional coordinates and directly fit the…
Text-video retrieval (TVR) has seen substantial advancements in recent years, fueled by the utilization of pre-trained models and large language models (LLMs). Despite these advancements, achieving accurate matching in TVR remains challenging due to inherent disparities between video and textual mod…
Multimodal large language models (MLLMs) combine visual and textual data for tasks like image captioning and visual question answering. Proper uncertainty calibration is crucial but challenging for reliable use in areas like healthcare and autonomous driving. This paper investigates several MLLMs, f…
We study text-based image editing (TBIE) of a single image by counterfactual inference because it is an elegant formulation to precisely address the requirement: the edited image should retain the fidelity of the original one. Through the lens of the formulation we find that the crux of TBIE is that…
Even when using large multi-modal foundation models few-shot learning is still challenging -- if there is no proper inductive bias it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end we…
In the real-world setting, data often follows a long-tailed distribution, where head classes contain significantly more training samples than tail classes. Consequently, models trained on such data tend to be biased toward head classes. The medium of this bias is imbalanced gradients, which include…
The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses, struggling to balance the desired properties of relia…
Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from gen…
Cognitive diagnosis is an important task in intelligence education, which aims at measuring students’ proficiency in specific knowledge concepts. Given a fully labeled exercise-concept matrix, most existing models focused on mining students' response records for cognitive diagnosis. Despite their su…
Video summarization and video captioning both condense the video content from the perspective of visual and text modes, i.e. the keyframe selection and language description generation. Existing video-and-language learning models commonly sample multiple frames for training instead of observing all.…
Recommender systems have been widely used in recent years. By exploiting historical user-item interactions, recommender systems can model personalized potential interests of users and have been widely applied to a wide range of scenarios. Despite their impressive performance, most of them may be sub…
Data-free quantization (DFQ) recovers the performance of quantized network (Q) without accessing the real data, but generates the fake sample via a generator (G) by learning from full-precision network (P) instead. However, such sample generation process is totally independence of Q, specialized as…
Low-light image enhancement focus on refining the illumination and keep naturalness to obtain the normal-light image. Current low-light image enhancement methods can well improve the illumination. However, there is still color difference between the enhanced image and the ground-truth image. To alle…
Multi-scale representation learning aims to leverage diverse features from different layers of Convolutional Neural Networks (CNNs) for boosting the feature robustness to scale variance. For dense prediction tasks, two key properties should be satisfied: the high spatial variance across convolutiona…
"Online Knowledge Distillation (OKD) improves the involved models by reciprocally exploiting the difference between teacher and student. Several crucial bottlenecks over the gap between them -- e.g., Why and when does a large gap harm the performance, especially for student? How to quantify the gap…
"We investigate the problem of estimating uncertainty for training data, so that deep neural networks can make use of the results for learning from limited supervision. However, both prediction probability and entropy estimate uncertainty from the instantaneous information. In this paper, we present…
In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval. There are two main f…
This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to query with a predicted label of each sample and learn from…
Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e.g., low-resolution, weak illumination, blurring and adverse weather. On the one hand, these degradations lead to severe discriminative information loss, which significantly obstructs identity…
Recent deep learning based person re-identification approaches have steadily improved the performance for benchmarks, however they often fail to generalize well from one domain to another. In this work, we propose a novel adaptive transfer network (ATNet) for effective cross-domain person re-identif…
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the product of low-rank kernels,the product of structured spars…
In recent years, many tracking algorithms achieve impressive performance via fusing multiple types of features, however, most of them fail to fully explore the context among the adopted multiple features and the strength of them. In this paper, we propose an efficient multi-cue analysis framework fo…
Knowing how hands move and what object is being manipulated are two key sub-tasks for analyzing first-person (egocentric) action. However, lack of fully annotated hand data as well as imprecise foreground segmentation make either sub-task challenging. This work aims to explicitly address these two i…
Modeling human-object interactions and manipulating motions lies in the heart of fine-grained action recognition. Previous methods heavily rely on explicit detection of the object being interacted, which requires intensive human labour on object annotation. To bypass this constraint and achieve bett…